{"id":2801,"date":"2026-01-19T11:38:40","date_gmt":"2026-01-19T11:38:40","guid":{"rendered":"https:\/\/www.digital-solutions.uk\/?p=2801"},"modified":"2026-01-19T11:40:59","modified_gmt":"2026-01-19T11:40:59","slug":"beyond-the-query-transforming-environmental-data-discovery-with-llms","status":"publish","type":"post","link":"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/","title":{"rendered":"Beyond the Query: Transforming Environmental Data Discovery with LLMs"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"2801\" class=\"elementor elementor-2801\">\n\t\t\t\t\t\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-2d23b45b elementor-section-boxed elementor-section-height-default elementor-section-height-default wpr-particle-no wpr-jarallax-no wpr-parallax-no wpr-sticky-section-no\" data-id=\"2d23b45b\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-215272ba\" data-id=\"215272ba\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-19b30ae6 elementor-widget elementor-widget-text-editor\" data-id=\"19b30ae6\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.13.3 - 28-05-2023 *\/\n.elementor-widget-text-editor.elementor-drop-cap-view-stacked .elementor-drop-cap{background-color:#69727d;color:#fff}.elementor-widget-text-editor.elementor-drop-cap-view-framed .elementor-drop-cap{color:#69727d;border:3px solid;background-color:transparent}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap{margin-top:8px}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap-letter{width:1em;height:1em}.elementor-widget-text-editor .elementor-drop-cap{float:left;text-align:center;line-height:1;font-size:50px}.elementor-widget-text-editor .elementor-drop-cap-letter{display:inline-block}<\/style>\t\t\t\t<p><!-- wp:paragraph --><\/p>\n<p><span style=\"font-size: 21px;\"><strong>By Professor David Topping | Originally published by Policy@Manchester<\/strong><\/span><\/p>\n<p class=\"MsoNormal\"><strong>Environmental problems are complex, evolving issues that defy straightforward solutions. These challenges demand integrated data, yet current environmental data is scattered and hard to access. Artificial intelligence (AI), alongside strong metadata frameworks, is emerging as a powerful tool for breaking down barriers to data discovery. Here <a href=\"https:\/\/research.manchester.ac.uk\/en\/persons\/david.topping\">Professor David Topping<\/a> outlines the importance of access to quality data in solving environmental problems, the issues associated with this access and suggests ways to unlock the potential for environmental data to inform real-world solutions in the UK.<\/strong><\/p>\n<ul>\n<li>The current state of environmental data access is unsatisfactory and restricts the potential for solutions to environmental problems.<\/li>\n<li>AI is emerging as a powerful tool to break down barriers to data discovery but lacking AI frameworks and metadata standards are hindering progress.<\/li>\n<li><a href=\"https:\/\/www.digital-solutions.uk\/\" target=\"_blank\" rel=\"noopener\">The NERC Digital Solutions Hub<\/a>\u00a0is a strong example of how AI and good metadata can be combined to improve environmental data access and inform solutions to \u2018wicked\u2019 environmental problems.<\/li>\n<\/ul>\n<p><span style=\"font-size: 18px;\"><strong style=\"letter-spacing: 0px;\">Access to environmental data is not FAIR<\/strong><\/span><\/p>\n<p>Data collection is integral to environmental science. Yet just as research efforts are siloed, so too are the\u00a0<a href=\"https:\/\/www.gov.uk\/government\/publications\/food-data-transparency-partnership-agri-food-environmental-data\/fdtp-towards-consistent-accurate-and-accessible-environmental-impact-quantification-for-the-agri-food-industry#:~:text=The%20rise%20of%20environmental%20impact,landscape%20of%20initiatives%2C%20approaches%20and\" target=\"_blank\" rel=\"noopener\">digital infrastructures<\/a>\u00a0that house environmental data in the UK. Although a\u00a0<a href=\"https:\/\/ioppublishing.org\/barriers-to-sharing-data-openly-data-sharing\/\" target=\"_blank\" rel=\"noopener\">recent review<\/a>\u00a0suggested that environmental science compares favourably to other disciplines in terms of alignment with the F<a href=\"https:\/\/www.go-fair.org\/fair-principles\/\" target=\"_blank\" rel=\"noopener\">AIR\u00a0<\/a>data principles,\u00a0<a href=\"https:\/\/www.digital-solutions.uk\/wp-content\/uploads\/2023\/09\/NERC-DSH-Report-ODM-FINAL.pdf\" target=\"_blank\" rel=\"noopener\">our consultations<\/a>\u00a0with environmental data users across the UK revealed significant and persistent barriers to data access and use. Open data, while commendable, is not necessarily discoverable or automatically useful.<span style=\"letter-spacing: 0px;\">\u00a0<\/span><\/p>\n<p>This presents a challenge for science and policy in the environmental domain. Many issues we face are known as \u2018wicked problems\u2019. These are complex, evolving issues that are hard to define, involve diverse and often conflicting interests, and defy straightforward solutions. Environmental problems are emblematic of this, as they sit at the intersection of ecological, social, economic, and political systems.<br \/>Such interconnected challenges demand equally integrated data. The current state of environmental data, which is scattered, unevenly curated, and often difficult to access, makes it hard to draw links between phenomena such as climate projections and health outcomes. The\u00a0<a href=\"https:\/\/ico.org.uk\/media2\/migrated\/2782\/inspire_regulations_2009_and_the_role_of_the_ico.pdf\" target=\"_blank\" rel=\"noopener\">INSPIRE Regulations 2009<\/a>\u00a0set out to counter this and facilitate better public access to spatial information across Europe, yet there is still much to be done to achieve this integration.<\/p>\n<p><span style=\"font-size: 18px;\"><strong style=\"letter-spacing: 0px;\">The role of AI and metadata in better data discovery<\/strong><\/span><\/p>\n<p>AI, especially Large Language Models (LLMs) offer a transformative opportunity in how we search and interact with data itself. Public attention has largely focused on the generative and conversational capabilities of LLMs, which have revolutionised search, discovery, and digital assistance. However, these same technologies can be harnessed for good to answer domain-specific questions that traditionally require expert triage and access to siloed data sources. Imagine visiting a platform and asking: \u201cWhat data can help me understand the impacts of transport emissions on public health?\u201d In the traditional model, a team of experts might unpack this into a series of scenarios, identify relevant datasets, and design an analytical pipeline. Assuming that they know where and how to access the right data.<\/p>\n<p>A key technology enabling this shift is\u00a0<a href=\"https:\/\/arxiv.org\/abs\/2510.01473\" target=\"_blank\" rel=\"noopener\">retrieval-augmented generation<\/a>. This approach allows LLMs to augment their responses by pulling in relevant information from external sources, be it documents, datasets, or structured metadata. If\u00a0<a href=\"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/02786826.2019.1664724\" target=\"_blank\" rel=\"noopener\">metadata describing datasets\u00a0<\/a>are embedded using this approach, then even imperfect or incomplete descriptions can still be matched semantically with user queries. Suppose a user asks for data on health impacts from mould exposure; a complex combination of atmospheric and clinical science, atmospheric monitoring and social behaviour. Even if the metadata doesn\u2019t explicitly mention mould but references composting emissions, an LLM might still identify the dataset by associating composting-related spores with respiratory outcomes thanks to its semantic understanding. LLMs can also be used to improve metadata quality by supplementing, standardising or inferring missing fields. Of course, there are evolving barriers around public trust of results generated from such tools, as discovered through\u00a0<a style=\"font-family: Roboto, sans-serif; background-color: #f5f5f5; letter-spacing: 0px;\" href=\"https:\/\/arxiv.org\/abs\/2510.01473\" target=\"_blank\" rel=\"noopener\">our recent research.<\/a><\/p>\n<p>The NERC Digital Solutions Programme, have worked directly with\u00a0<a href=\"https:\/\/www.digital-solutions.uk\/index.php\/the-second-user-research-report-for-the-dsh-is-released\/\" target=\"_blank\" rel=\"noopener\">environmental data users<\/a>\u00a0to ensure that AI-powered tools available on the NERC Digital Solutions Hub (DSH) are grounded in practical needs. By integrating LLMs with strong metadata frameworks and participatory design, the DSH empowers policymakers to discover evidence more efficiently, trace its provenance, and apply it with confidence to\u00a0<a href=\"https:\/\/www.digital-solutions.uk\/index.php\/geoai-overcoming-the-hype-and-avoiding-hallucinations\/\" target=\"_blank\" rel=\"noopener\">address urgent environmental challenges.<\/a>\u00a0In doing so, we are not just improving data access, we are reimagining what responsive, AI-enhanced environmental science can look like.<\/p>\n<p><span style=\"font-size: 18px;\"><strong>Centre Environmental Problem-Holders in Policy Design<\/strong><\/span><\/p>\n<p>Policymakers should be at the forefront of technological development. By engaging directly with initiatives like the DSH, they gain early visibility into practical use cases, opportunities, and challenges. This insight enables them to advocate for and shape policy that supports innovation while ensuring ethical, equitable, and sustainable deployment. This is timely as the UK government\u2019s\u00a0<a href=\"https:\/\/www.gov.uk\/government\/publications\/ai-opportunities-action-plan\/ai-opportunities-action-plan\" target=\"_blank\" rel=\"noopener\">AI Action Plan<\/a>\u00a0acknowledges that trustworthy, high-performing AI will be essential to achieving the government\u2019s missions, from building an<a href=\"https:\/\/www.gov.uk\/missions\/nhs\"> NHS fit for the future <\/a>to making Britain a\u00a0<a href=\"https:\/\/www.gov.uk\/missions\/clean-energy\" target=\"_blank\" rel=\"noopener\">clean energy superpower<\/a>.<\/p>\n<p>Regulations and investment strategies should reflect the realities of interdisciplinary, applied science and support actionable insights. To strengthen engagement with on-the-ground expertise this could include establishing a cross-sector expert panel focused on AI and environmental data, like that seen in GO-Science, with rotating membership from academia, public bodies, and practitioners, therefore embedding more agile, domain-specific expertise into government decision-making.<\/p>\n<p><span style=\"font-size: 18px;\"><strong>Build Capacity Within Public Sector Organisations<\/strong><\/span><\/p>\n<p>Whilst the UK\u2019s principles-based approach differs from other developing global governance models for generative AI, emerging collaboration agreements between the EU and UK will support joint development of new tools around, for example, AI factories. This might lead to appropriate governance by design. However, to effectively address the challenges of fragmented data landscapes and unlock the potential of AI technologies, all policy-driving organisations, including government departments and local authorities, should develop or update their AI strategies.<\/p>\n<p>The<a href=\"https:\/\/gds.blog.gov.uk\/2025\/02\/10\/launching-the-artificial-intelligence-playbook-for-the-uk-government\/\" target=\"_blank\" rel=\"noopener\"> AI playbook<\/a>, released this year, provides government departments and public sector organisations with accessible technical guidance on the safe and effective use of AI. However, they\u00a0<a href=\"https:\/\/www.gov.uk\/government\/publications\/science-and-technology-framework\/science-and-technology-framework\" target=\"_blank\" rel=\"noopener\">need to go furthe<\/a>r so that government can ensure their public services can deliver the best possible outcomes for citizens and businesses across the UK. The Department for Science, Innovation and Technology (DSIT) should ensure that AI strategies are grounded in a clear understanding of the current data ecosystem, the evolving landscape of generative AI tools, and infrastructure needed to enable responsible, scalable adoption. To achieve this, DSIT should invest in training and infrastructure, and facilitate access to expert guidance within government agencies to assist with their AI strategies. If public sector bodies move quickly to adopt and model good data practices, they can set visible standards that places constructive pressure.<\/p>\n<p>Now is the time to explore the use of LLMs for data search and discovery. A growing ecosystem of tools and platforms already exists, many of which can be trialled with minimal investment and without becoming dependent on proprietary solutions.<\/p>\n<p>These tools, such as the\u00a0<a href=\"https:\/\/www.digital-solutions.uk\/\" target=\"_blank\" rel=\"noopener\">DSH<\/a>, are not only accessible but are being taught and adopted by the next generation of scientists, analysts, and civil servants. Building awareness, testing these technologies in real-world contexts, and learning from early implementation efforts is a cost-effective, future-proof step that organisations can take now.<\/p>\n<p><!-- \/wp:paragraph --><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-c86b409 elementor-section-boxed elementor-section-height-default elementor-section-height-default wpr-particle-no wpr-jarallax-no wpr-parallax-no wpr-sticky-section-no\" data-id=\"c86b409\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-fe3010b\" data-id=\"fe3010b\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap\">\n\t\t\t\t\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>By Professor David Topping | Originally published by Policy@Manchester Environmental problems are complex, evolving issues that defy straightforward solutions. These challenges demand integrated data, yet current environmental data is scattered and hard to access. Artificial intelligence (AI), alongside strong metadata frameworks, is emerging as a powerful tool for breaking down barriers to data discovery. Here Professor David Topping outlines the importance of access to quality data in solving environmental problems, the issues associated with this access and suggests ways to unlock the potential for environmental data to inform real-world solutions in the UK. The current state of environmental data access is unsatisfactory and restricts the potential for solutions to environmental problems. AI is emerging as a powerful tool to break down barriers to data discovery but lacking AI frameworks and metadata standards are hindering progress. The NERC Digital Solutions Hub\u00a0is a strong example of how AI and good metadata can be combined to improve environmental data access and inform solutions to \u2018wicked\u2019 environmental problems. Access to environmental data is not FAIR Data collection is integral to environmental science. Yet just as research efforts are siloed, so too are the\u00a0digital infrastructures\u00a0that house environmental data in the UK. Although a\u00a0recent review\u00a0suggested that environmental science compares favourably to other disciplines in terms of alignment with the FAIR\u00a0data principles,\u00a0our consultations\u00a0with environmental data users across the UK revealed significant and persistent barriers to data access and use. Open data, while commendable, is not necessarily discoverable or automatically useful.\u00a0 This presents a challenge for science and policy in the environmental domain. Many issues we face are known as \u2018wicked problems\u2019. These are complex, evolving issues that are hard to define, involve diverse and often conflicting interests, and defy straightforward solutions. Environmental problems are emblematic of this, as they sit at the intersection of ecological, social, economic, and political systems.Such interconnected challenges demand equally integrated data. The current state of environmental data, which is scattered, unevenly curated, and often difficult to access, makes it hard to draw links between phenomena such as climate projections and health outcomes. The\u00a0INSPIRE Regulations 2009\u00a0set out to counter this and facilitate better public access to spatial information across Europe, yet there is still much to be done to achieve this integration. The role of AI and metadata in better data discovery AI, especially Large Language Models (LLMs) offer a transformative opportunity in how we search and interact with data itself. Public attention has largely focused on the generative and conversational capabilities of LLMs, which have revolutionised search, discovery, and digital assistance. However, these same technologies can be harnessed for good to answer domain-specific questions that traditionally require expert triage and access to siloed data sources. Imagine visiting a platform and asking: \u201cWhat data can help me understand the impacts of transport emissions on public health?\u201d In the traditional model, a team of experts might unpack this into a series of scenarios, identify relevant datasets, and design an analytical pipeline. Assuming that they know where and how to access the right data. A key technology enabling this shift is\u00a0retrieval-augmented generation. This approach allows LLMs to augment their responses by pulling in relevant information from external sources, be it documents, datasets, or structured metadata. If\u00a0metadata describing datasets\u00a0are embedded using this approach, then even imperfect or incomplete descriptions can still be matched semantically with user queries. Suppose a user asks for data on health impacts from mould exposure; a complex combination of atmospheric and clinical science, atmospheric monitoring and social behaviour. Even if the metadata doesn\u2019t explicitly mention mould but references composting emissions, an LLM might still identify the dataset by associating composting-related spores with respiratory outcomes thanks to its semantic understanding. LLMs can also be used to improve metadata quality by supplementing, standardising or inferring missing fields. Of course, there are evolving barriers around public trust of results generated from such tools, as discovered through\u00a0our recent research. The NERC Digital Solutions Programme, have worked directly with\u00a0environmental data users\u00a0to ensure that AI-powered tools available on the NERC Digital Solutions Hub (DSH) are grounded in practical needs. By integrating LLMs with strong metadata frameworks and participatory design, the DSH empowers policymakers to discover evidence more efficiently, trace its provenance, and apply it with confidence to\u00a0address urgent environmental challenges.\u00a0In doing so, we are not just improving data access, we are reimagining what responsive, AI-enhanced environmental science can look like. Centre Environmental Problem-Holders in Policy Design Policymakers should be at the forefront of technological development. By engaging directly with initiatives like the DSH, they gain early visibility into practical use cases, opportunities, and challenges. This insight enables them to advocate for and shape policy that supports innovation while ensuring ethical, equitable, and sustainable deployment. This is timely as the UK government\u2019s\u00a0AI Action Plan\u00a0acknowledges that trustworthy, high-performing AI will be essential to achieving the government\u2019s missions, from building an NHS fit for the future to making Britain a\u00a0clean energy superpower. Regulations and investment strategies should reflect the realities of interdisciplinary, applied science and support actionable insights. To strengthen engagement with on-the-ground expertise this could include establishing a cross-sector expert panel focused on AI and environmental data, like that seen in GO-Science, with rotating membership from academia, public bodies, and practitioners, therefore embedding more agile, domain-specific expertise into government decision-making. Build Capacity Within Public Sector Organisations Whilst the UK\u2019s principles-based approach differs from other developing global governance models for generative AI, emerging collaboration agreements between the EU and UK will support joint development of new tools around, for example, AI factories. This might lead to appropriate governance by design. However, to effectively address the challenges of fragmented data landscapes and unlock the potential of AI technologies, all policy-driving organisations, including government departments and local authorities, should develop or update their AI strategies. The AI playbook, released this year, provides government departments and public sector organisations with accessible technical guidance on the safe and effective use of AI. However, they\u00a0need to go further so that government can ensure their public services can deliver the best possible outcomes for citizens and businesses across the UK. The Department for Science, Innovation and Technology (DSIT) should ensure that AI strategies are grounded in a clear understanding of the current data ecosystem, the evolving landscape of generative AI tools, and infrastructure needed to enable responsible, scalable adoption. To achieve this, DSIT should invest in training and infrastructure, and facilitate access to expert guidance within government agencies to assist with their AI strategies. If public sector bodies move quickly to adopt and model good data practices, they can set visible standards that places constructive pressure. Now is the time to explore the use of LLMs for data search and discovery. A growing ecosystem of tools and platforms already exists, many of which can be trialled with minimal investment and without becoming dependent on proprietary solutions. These tools, such as the\u00a0DSH, are not only accessible but are being taught and adopted by the next generation of scientists, analysts, and civil servants. Building awareness, testing these technologies in real-world contexts, and learning from early implementation efforts is a cost-effective, future-proof step that organisations can take now.<\/p>\n","protected":false},"author":7,"featured_media":2802,"comment_status":"closed","ping_status":"open","sticky":true,"template":"","format":"standard","meta":[],"categories":[18],"tags":[33,20,23,22,24,21],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v20.8 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Beyond the Query: Transforming Environmental Data Discovery with LLMs - NERC Digital Solutions Programme<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Beyond the Query: Transforming Environmental Data Discovery with LLMs - NERC Digital Solutions Programme\" \/>\n<meta property=\"og:description\" content=\"By Professor David Topping | Originally published by Policy@Manchester Environmental problems are complex, evolving issues that defy straightforward solutions. These challenges demand integrated data, yet current environmental data is scattered and hard to access. Artificial intelligence (AI), alongside strong metadata frameworks, is emerging as a powerful tool for breaking down barriers to data discovery. Here Professor David Topping outlines the importance of access to quality data in solving environmental problems, the issues associated with this access and suggests ways to unlock the potential for environmental data to inform real-world solutions in the UK. The current state of environmental data access is unsatisfactory and restricts the potential for solutions to environmental problems. AI is emerging as a powerful tool to break down barriers to data discovery but lacking AI frameworks and metadata standards are hindering progress. The NERC Digital Solutions Hub\u00a0is a strong example of how AI and good metadata can be combined to improve environmental data access and inform solutions to \u2018wicked\u2019 environmental problems. Access to environmental data is not FAIR Data collection is integral to environmental science. Yet just as research efforts are siloed, so too are the\u00a0digital infrastructures\u00a0that house environmental data in the UK. Although a\u00a0recent review\u00a0suggested that environmental science compares favourably to other disciplines in terms of alignment with the FAIR\u00a0data principles,\u00a0our consultations\u00a0with environmental data users across the UK revealed significant and persistent barriers to data access and use. Open data, while commendable, is not necessarily discoverable or automatically useful.\u00a0 This presents a challenge for science and policy in the environmental domain. Many issues we face are known as \u2018wicked problems\u2019. These are complex, evolving issues that are hard to define, involve diverse and often conflicting interests, and defy straightforward solutions. Environmental problems are emblematic of this, as they sit at the intersection of ecological, social, economic, and political systems.Such interconnected challenges demand equally integrated data. The current state of environmental data, which is scattered, unevenly curated, and often difficult to access, makes it hard to draw links between phenomena such as climate projections and health outcomes. The\u00a0INSPIRE Regulations 2009\u00a0set out to counter this and facilitate better public access to spatial information across Europe, yet there is still much to be done to achieve this integration. The role of AI and metadata in better data discovery AI, especially Large Language Models (LLMs) offer a transformative opportunity in how we search and interact with data itself. Public attention has largely focused on the generative and conversational capabilities of LLMs, which have revolutionised search, discovery, and digital assistance. However, these same technologies can be harnessed for good to answer domain-specific questions that traditionally require expert triage and access to siloed data sources. Imagine visiting a platform and asking: \u201cWhat data can help me understand the impacts of transport emissions on public health?\u201d In the traditional model, a team of experts might unpack this into a series of scenarios, identify relevant datasets, and design an analytical pipeline. Assuming that they know where and how to access the right data. A key technology enabling this shift is\u00a0retrieval-augmented generation. This approach allows LLMs to augment their responses by pulling in relevant information from external sources, be it documents, datasets, or structured metadata. If\u00a0metadata describing datasets\u00a0are embedded using this approach, then even imperfect or incomplete descriptions can still be matched semantically with user queries. Suppose a user asks for data on health impacts from mould exposure; a complex combination of atmospheric and clinical science, atmospheric monitoring and social behaviour. Even if the metadata doesn\u2019t explicitly mention mould but references composting emissions, an LLM might still identify the dataset by associating composting-related spores with respiratory outcomes thanks to its semantic understanding. LLMs can also be used to improve metadata quality by supplementing, standardising or inferring missing fields. Of course, there are evolving barriers around public trust of results generated from such tools, as discovered through\u00a0our recent research. The NERC Digital Solutions Programme, have worked directly with\u00a0environmental data users\u00a0to ensure that AI-powered tools available on the NERC Digital Solutions Hub (DSH) are grounded in practical needs. By integrating LLMs with strong metadata frameworks and participatory design, the DSH empowers policymakers to discover evidence more efficiently, trace its provenance, and apply it with confidence to\u00a0address urgent environmental challenges.\u00a0In doing so, we are not just improving data access, we are reimagining what responsive, AI-enhanced environmental science can look like. Centre Environmental Problem-Holders in Policy Design Policymakers should be at the forefront of technological development. By engaging directly with initiatives like the DSH, they gain early visibility into practical use cases, opportunities, and challenges. This insight enables them to advocate for and shape policy that supports innovation while ensuring ethical, equitable, and sustainable deployment. This is timely as the UK government\u2019s\u00a0AI Action Plan\u00a0acknowledges that trustworthy, high-performing AI will be essential to achieving the government\u2019s missions, from building an NHS fit for the future to making Britain a\u00a0clean energy superpower. Regulations and investment strategies should reflect the realities of interdisciplinary, applied science and support actionable insights. To strengthen engagement with on-the-ground expertise this could include establishing a cross-sector expert panel focused on AI and environmental data, like that seen in GO-Science, with rotating membership from academia, public bodies, and practitioners, therefore embedding more agile, domain-specific expertise into government decision-making. Build Capacity Within Public Sector Organisations Whilst the UK\u2019s principles-based approach differs from other developing global governance models for generative AI, emerging collaboration agreements between the EU and UK will support joint development of new tools around, for example, AI factories. This might lead to appropriate governance by design. However, to effectively address the challenges of fragmented data landscapes and unlock the potential of AI technologies, all policy-driving organisations, including government departments and local authorities, should develop or update their AI strategies. The AI playbook, released this year, provides government departments and public sector organisations with accessible technical guidance on the safe and effective use of AI. However, they\u00a0need to go further so that government can ensure their public services can deliver the best possible outcomes for citizens and businesses across the UK. The Department for Science, Innovation and Technology (DSIT) should ensure that AI strategies are grounded in a clear understanding of the current data ecosystem, the evolving landscape of generative AI tools, and infrastructure needed to enable responsible, scalable adoption. To achieve this, DSIT should invest in training and infrastructure, and facilitate access to expert guidance within government agencies to assist with their AI strategies. If public sector bodies move quickly to adopt and model good data practices, they can set visible standards that places constructive pressure. Now is the time to explore the use of LLMs for data search and discovery. A growing ecosystem of tools and platforms already exists, many of which can be trialled with minimal investment and without becoming dependent on proprietary solutions. These tools, such as the\u00a0DSH, are not only accessible but are being taught and adopted by the next generation of scientists, analysts, and civil servants. Building awareness, testing these technologies in real-world contexts, and learning from early implementation efforts is a cost-effective, future-proof step that organisations can take now.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/\" \/>\n<meta property=\"og:site_name\" content=\"NERC Digital Solutions Programme\" \/>\n<meta property=\"article:published_time\" content=\"2026-01-19T11:38:40+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-01-19T11:40:59+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.digital-solutions.uk\/wp-content\/uploads\/2026\/01\/AI-and-Data-image.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"960\" \/>\n\t<meta property=\"og:image:height\" content=\"300\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Digital Solutions\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@NERCdsh\" \/>\n<meta name=\"twitter:site\" content=\"@NERCdsh\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Digital Solutions\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimated reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/\"},\"author\":{\"name\":\"Digital Solutions\",\"@id\":\"https:\/\/www.digital-solutions.uk\/#\/schema\/person\/15e49da67fd44c8c7e7af042d6780933\"},\"headline\":\"Beyond the Query: Transforming Environmental Data Discovery with LLMs\",\"datePublished\":\"2026-01-19T11:38:40+00:00\",\"dateModified\":\"2026-01-19T11:40:59+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/\"},\"wordCount\":1214,\"publisher\":{\"@id\":\"https:\/\/www.digital-solutions.uk\/#organization\"},\"keywords\":[\"AI\",\"data\",\"DSH\",\"Environment\",\"NERC\",\"policy making\"],\"articleSection\":[\"All posts\"],\"inLanguage\":\"en-GB\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/\",\"url\":\"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/\",\"name\":\"Beyond the Query: Transforming Environmental Data Discovery with LLMs - NERC Digital Solutions Programme\",\"isPartOf\":{\"@id\":\"https:\/\/www.digital-solutions.uk\/#website\"},\"datePublished\":\"2026-01-19T11:38:40+00:00\",\"dateModified\":\"2026-01-19T11:40:59+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/#breadcrumb\"},\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.digital-solutions.uk\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Beyond the Query: Transforming Environmental Data Discovery with LLMs\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.digital-solutions.uk\/#website\",\"url\":\"https:\/\/www.digital-solutions.uk\/\",\"name\":\"NERC Digital Solutions Programme\",\"description\":\"Developing a Digital Hub and set of Toolkits that exploits environmental and other data (social, economic &amp; health) to create innovative digital services that deliver economic, societal and environmental benefits across the UK\",\"publisher\":{\"@id\":\"https:\/\/www.digital-solutions.uk\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.digital-solutions.uk\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-GB\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.digital-solutions.uk\/#organization\",\"name\":\"NERC Digital Solutions Programme\",\"url\":\"https:\/\/www.digital-solutions.uk\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/www.digital-solutions.uk\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.digital-solutions.uk\/wp-content\/uploads\/2022\/09\/cropped-DSH-logo_sq.jpg\",\"contentUrl\":\"https:\/\/www.digital-solutions.uk\/wp-content\/uploads\/2022\/09\/cropped-DSH-logo_sq.jpg\",\"width\":525,\"height\":523,\"caption\":\"NERC Digital Solutions Programme\"},\"image\":{\"@id\":\"https:\/\/www.digital-solutions.uk\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/twitter.com\/NERCdsh\",\"https:\/\/www.linkedin.com\/company\/nerc-digital-solutions-hub\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.digital-solutions.uk\/#\/schema\/person\/15e49da67fd44c8c7e7af042d6780933\",\"name\":\"Digital Solutions\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/www.digital-solutions.uk\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/5eb2bae037492922425d4446edf664d4?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/5eb2bae037492922425d4446edf664d4?s=96&d=mm&r=g\",\"caption\":\"Digital Solutions\"},\"sameAs\":[\"https:\/\/www.digital-solutions.uk\/\"],\"url\":\"https:\/\/www.digital-solutions.uk\/index.php\/author\/dsh\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Beyond the Query: Transforming Environmental Data Discovery with LLMs - NERC Digital Solutions Programme","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/","og_locale":"en_GB","og_type":"article","og_title":"Beyond the Query: Transforming Environmental Data Discovery with LLMs - NERC Digital Solutions Programme","og_description":"By Professor David Topping | Originally published by Policy@Manchester Environmental problems are complex, evolving issues that defy straightforward solutions. These challenges demand integrated data, yet current environmental data is scattered and hard to access. Artificial intelligence (AI), alongside strong metadata frameworks, is emerging as a powerful tool for breaking down barriers to data discovery. Here Professor David Topping outlines the importance of access to quality data in solving environmental problems, the issues associated with this access and suggests ways to unlock the potential for environmental data to inform real-world solutions in the UK. The current state of environmental data access is unsatisfactory and restricts the potential for solutions to environmental problems. AI is emerging as a powerful tool to break down barriers to data discovery but lacking AI frameworks and metadata standards are hindering progress. The NERC Digital Solutions Hub\u00a0is a strong example of how AI and good metadata can be combined to improve environmental data access and inform solutions to \u2018wicked\u2019 environmental problems. Access to environmental data is not FAIR Data collection is integral to environmental science. Yet just as research efforts are siloed, so too are the\u00a0digital infrastructures\u00a0that house environmental data in the UK. Although a\u00a0recent review\u00a0suggested that environmental science compares favourably to other disciplines in terms of alignment with the FAIR\u00a0data principles,\u00a0our consultations\u00a0with environmental data users across the UK revealed significant and persistent barriers to data access and use. Open data, while commendable, is not necessarily discoverable or automatically useful.\u00a0 This presents a challenge for science and policy in the environmental domain. Many issues we face are known as \u2018wicked problems\u2019. These are complex, evolving issues that are hard to define, involve diverse and often conflicting interests, and defy straightforward solutions. Environmental problems are emblematic of this, as they sit at the intersection of ecological, social, economic, and political systems.Such interconnected challenges demand equally integrated data. The current state of environmental data, which is scattered, unevenly curated, and often difficult to access, makes it hard to draw links between phenomena such as climate projections and health outcomes. The\u00a0INSPIRE Regulations 2009\u00a0set out to counter this and facilitate better public access to spatial information across Europe, yet there is still much to be done to achieve this integration. The role of AI and metadata in better data discovery AI, especially Large Language Models (LLMs) offer a transformative opportunity in how we search and interact with data itself. Public attention has largely focused on the generative and conversational capabilities of LLMs, which have revolutionised search, discovery, and digital assistance. However, these same technologies can be harnessed for good to answer domain-specific questions that traditionally require expert triage and access to siloed data sources. Imagine visiting a platform and asking: \u201cWhat data can help me understand the impacts of transport emissions on public health?\u201d In the traditional model, a team of experts might unpack this into a series of scenarios, identify relevant datasets, and design an analytical pipeline. Assuming that they know where and how to access the right data. A key technology enabling this shift is\u00a0retrieval-augmented generation. This approach allows LLMs to augment their responses by pulling in relevant information from external sources, be it documents, datasets, or structured metadata. If\u00a0metadata describing datasets\u00a0are embedded using this approach, then even imperfect or incomplete descriptions can still be matched semantically with user queries. Suppose a user asks for data on health impacts from mould exposure; a complex combination of atmospheric and clinical science, atmospheric monitoring and social behaviour. Even if the metadata doesn\u2019t explicitly mention mould but references composting emissions, an LLM might still identify the dataset by associating composting-related spores with respiratory outcomes thanks to its semantic understanding. LLMs can also be used to improve metadata quality by supplementing, standardising or inferring missing fields. Of course, there are evolving barriers around public trust of results generated from such tools, as discovered through\u00a0our recent research. The NERC Digital Solutions Programme, have worked directly with\u00a0environmental data users\u00a0to ensure that AI-powered tools available on the NERC Digital Solutions Hub (DSH) are grounded in practical needs. By integrating LLMs with strong metadata frameworks and participatory design, the DSH empowers policymakers to discover evidence more efficiently, trace its provenance, and apply it with confidence to\u00a0address urgent environmental challenges.\u00a0In doing so, we are not just improving data access, we are reimagining what responsive, AI-enhanced environmental science can look like. Centre Environmental Problem-Holders in Policy Design Policymakers should be at the forefront of technological development. By engaging directly with initiatives like the DSH, they gain early visibility into practical use cases, opportunities, and challenges. This insight enables them to advocate for and shape policy that supports innovation while ensuring ethical, equitable, and sustainable deployment. This is timely as the UK government\u2019s\u00a0AI Action Plan\u00a0acknowledges that trustworthy, high-performing AI will be essential to achieving the government\u2019s missions, from building an NHS fit for the future to making Britain a\u00a0clean energy superpower. Regulations and investment strategies should reflect the realities of interdisciplinary, applied science and support actionable insights. To strengthen engagement with on-the-ground expertise this could include establishing a cross-sector expert panel focused on AI and environmental data, like that seen in GO-Science, with rotating membership from academia, public bodies, and practitioners, therefore embedding more agile, domain-specific expertise into government decision-making. Build Capacity Within Public Sector Organisations Whilst the UK\u2019s principles-based approach differs from other developing global governance models for generative AI, emerging collaboration agreements between the EU and UK will support joint development of new tools around, for example, AI factories. This might lead to appropriate governance by design. However, to effectively address the challenges of fragmented data landscapes and unlock the potential of AI technologies, all policy-driving organisations, including government departments and local authorities, should develop or update their AI strategies. The AI playbook, released this year, provides government departments and public sector organisations with accessible technical guidance on the safe and effective use of AI. However, they\u00a0need to go further so that government can ensure their public services can deliver the best possible outcomes for citizens and businesses across the UK. The Department for Science, Innovation and Technology (DSIT) should ensure that AI strategies are grounded in a clear understanding of the current data ecosystem, the evolving landscape of generative AI tools, and infrastructure needed to enable responsible, scalable adoption. To achieve this, DSIT should invest in training and infrastructure, and facilitate access to expert guidance within government agencies to assist with their AI strategies. If public sector bodies move quickly to adopt and model good data practices, they can set visible standards that places constructive pressure. Now is the time to explore the use of LLMs for data search and discovery. A growing ecosystem of tools and platforms already exists, many of which can be trialled with minimal investment and without becoming dependent on proprietary solutions. These tools, such as the\u00a0DSH, are not only accessible but are being taught and adopted by the next generation of scientists, analysts, and civil servants. Building awareness, testing these technologies in real-world contexts, and learning from early implementation efforts is a cost-effective, future-proof step that organisations can take now.","og_url":"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/","og_site_name":"NERC Digital Solutions Programme","article_published_time":"2026-01-19T11:38:40+00:00","article_modified_time":"2026-01-19T11:40:59+00:00","og_image":[{"url":"https:\/\/www.digital-solutions.uk\/wp-content\/uploads\/2026\/01\/AI-and-Data-image.jpg","width":960,"height":300,"type":"image\/jpeg"}],"author":"Digital Solutions","twitter_card":"summary_large_image","twitter_creator":"@NERCdsh","twitter_site":"@NERCdsh","twitter_misc":{"Written by":"Digital Solutions","Estimated reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/#article","isPartOf":{"@id":"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/"},"author":{"name":"Digital Solutions","@id":"https:\/\/www.digital-solutions.uk\/#\/schema\/person\/15e49da67fd44c8c7e7af042d6780933"},"headline":"Beyond the Query: Transforming Environmental Data Discovery with LLMs","datePublished":"2026-01-19T11:38:40+00:00","dateModified":"2026-01-19T11:40:59+00:00","mainEntityOfPage":{"@id":"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/"},"wordCount":1214,"publisher":{"@id":"https:\/\/www.digital-solutions.uk\/#organization"},"keywords":["AI","data","DSH","Environment","NERC","policy making"],"articleSection":["All posts"],"inLanguage":"en-GB"},{"@type":"WebPage","@id":"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/","url":"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/","name":"Beyond the Query: Transforming Environmental Data Discovery with LLMs - NERC Digital Solutions Programme","isPartOf":{"@id":"https:\/\/www.digital-solutions.uk\/#website"},"datePublished":"2026-01-19T11:38:40+00:00","dateModified":"2026-01-19T11:40:59+00:00","breadcrumb":{"@id":"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/#breadcrumb"},"inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.digital-solutions.uk\/index.php\/beyond-the-query-transforming-environmental-data-discovery-with-llms\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.digital-solutions.uk\/"},{"@type":"ListItem","position":2,"name":"Beyond the Query: Transforming Environmental Data Discovery with LLMs"}]},{"@type":"WebSite","@id":"https:\/\/www.digital-solutions.uk\/#website","url":"https:\/\/www.digital-solutions.uk\/","name":"NERC Digital Solutions Programme","description":"Developing a Digital Hub and set of Toolkits that exploits environmental and other data (social, economic &amp; health) to create innovative digital services that deliver economic, societal and environmental benefits across the UK","publisher":{"@id":"https:\/\/www.digital-solutions.uk\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.digital-solutions.uk\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-GB"},{"@type":"Organization","@id":"https:\/\/www.digital-solutions.uk\/#organization","name":"NERC Digital Solutions Programme","url":"https:\/\/www.digital-solutions.uk\/","logo":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/www.digital-solutions.uk\/#\/schema\/logo\/image\/","url":"https:\/\/www.digital-solutions.uk\/wp-content\/uploads\/2022\/09\/cropped-DSH-logo_sq.jpg","contentUrl":"https:\/\/www.digital-solutions.uk\/wp-content\/uploads\/2022\/09\/cropped-DSH-logo_sq.jpg","width":525,"height":523,"caption":"NERC Digital Solutions Programme"},"image":{"@id":"https:\/\/www.digital-solutions.uk\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/twitter.com\/NERCdsh","https:\/\/www.linkedin.com\/company\/nerc-digital-solutions-hub\/"]},{"@type":"Person","@id":"https:\/\/www.digital-solutions.uk\/#\/schema\/person\/15e49da67fd44c8c7e7af042d6780933","name":"Digital Solutions","image":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/www.digital-solutions.uk\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/5eb2bae037492922425d4446edf664d4?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/5eb2bae037492922425d4446edf664d4?s=96&d=mm&r=g","caption":"Digital Solutions"},"sameAs":["https:\/\/www.digital-solutions.uk\/"],"url":"https:\/\/www.digital-solutions.uk\/index.php\/author\/dsh\/"}]}},"_links":{"self":[{"href":"https:\/\/www.digital-solutions.uk\/index.php\/wp-json\/wp\/v2\/posts\/2801"}],"collection":[{"href":"https:\/\/www.digital-solutions.uk\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.digital-solutions.uk\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.digital-solutions.uk\/index.php\/wp-json\/wp\/v2\/users\/7"}],"replies":[{"embeddable":true,"href":"https:\/\/www.digital-solutions.uk\/index.php\/wp-json\/wp\/v2\/comments?post=2801"}],"version-history":[{"count":15,"href":"https:\/\/www.digital-solutions.uk\/index.php\/wp-json\/wp\/v2\/posts\/2801\/revisions"}],"predecessor-version":[{"id":2819,"href":"https:\/\/www.digital-solutions.uk\/index.php\/wp-json\/wp\/v2\/posts\/2801\/revisions\/2819"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.digital-solutions.uk\/index.php\/wp-json\/wp\/v2\/media\/2802"}],"wp:attachment":[{"href":"https:\/\/www.digital-solutions.uk\/index.php\/wp-json\/wp\/v2\/media?parent=2801"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.digital-solutions.uk\/index.php\/wp-json\/wp\/v2\/categories?post=2801"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.digital-solutions.uk\/index.php\/wp-json\/wp\/v2\/tags?post=2801"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}