General purpose

• ESRI ArcGIS Proprietary desktop and Online GIS with machine learning and deep learning tools for spatial and other analyses. Living Earth repository of pretrained models. Pretrained Deep Learning Models; Deep learning models in arcgis.learn ; Installation support for Deep Learning Frameworks for the ArcGIS System
• The free open source QGIS GIS has a variety of ML/AI extensions that call external libraries such as tensorflow. Tag: ai — QGIS Python Plugins Repository; Tag: ml — QGIS Python Plugins Repository; Machine Learning – QGIS Plugins; Deep Learning – QGIS Plugins
• Deep-Learning-Applications-with-GUI – list of FOSS Deep Learning (Desktop) Applications with GUI and/or CLI. Most Deep Learning models require a complicated setup and are not ready to use out of the box. At best there is a Colab or Jupiter notebook available, which is good for testing, but not for production use.
• MaxEnt Maximum entropy species distribution modelling. https://biodiversityinformatics.amnh.org/open_source/maxent/
• SPSS proprietary statistics program supports multilayer perceptron (MLP) or radial basis function (RBF) neural networks. Machine learning is another program IBM SPSS Modeler.
• ENNUI – an FOSS neural network interface.
• Nengo Brain Maker is a Python package for building, testing, and deploying neural networks.
• Perceptilabs – A GUI for TensorFlow, a new visual way to build models.
• Markersite – unlock the power of AI and graph technology with Makersite. Collaborate with your team to develop compliant, safe, cost-effective, and environmentally friendly products.

Task specific

• OSDG is a free, open-source tool that assigns SDG labels to your input.
• This Climate Does Not Exist free AI image generation tool that lets you imagine the impact of the climate crisis we face.
• Zevero combines AI-powered software with in-house sustainability experts to help track emissions, build a net zero strategy, and turn climate data into action.
• Clarity AI – invest sustainably, shop sustainably, and report or benchmark for sustainability with easy-to-use, AI-powered technology.
• AgroScout AI-driven crop intelligence.
• Deep Planet secure agricultural productivity and resilience at scale with AI.
• Net0 Enterprise AI Platform for Corporate Sustainability.
• Projective Group – 16 AI tools re-shaping the ESG and sustainable finance landscape.
• Sneider Electric AI solutions for power management.
• C3.ai energy management.
• Sidarel enegi Climate Resilience Toolkit for Cities & Communities. Three complementary, data-driven visualization and simulation solutions that help cities anticipate and adapt to climate change.
• GreyParrot AI intelligence for waste processing.
• RecycleEye AI intelligence for waste processing.
• reibred textile detection via hyperspectral imaging and AI.
• AMCS Vision AI is an artificial intelligence-driven solution designed to detect contamination in waste and recyclable streams, and overfilled containers, to enable companies to educate or charge customers.
• Mapmorter AI-driven building management.
• TaKaDu employs advanced statistical techniques and machine learning to detect and manage failures in water supply networks, such as leaks, early in their evolution, often when no other indications are available.
• AI Climate is a decision making/mapping tool for climate-resilience planning geared to secondary and tertiary cities and their regions which lack data at the local level and have limited technical capacity and resources. It uses machine learning (ML) technology that processes geospatial imagery and geo-referenced datasets, deriving data in the form of analytics-ready-layers such as impacts of flooding, landslides, land degradation, and others specific to the region.
• ClimateLens combines AI, advanced machine learning, and data points from multiple sources to generate actionable insights. The technology helps businesses and governments to adapt their operations and supply chains, as well as to identify opportunities, such as new locations for climate-smart expansion or increased demand for weather-dependent goods.
• Top 12+ Successful Sustainability Case Studies in 2025 (Arslan/AIMultipeResearch, 2025).
• Early Warnings for All is a UN initiative to ensure that everyone on Earth is protected from hazardous weather, water, or climate events through life-saving early warning systems by the end of 2027 that has AI components.

Large language models

Various LLMs are available each of which has advantages and disadvantages. LLMs are often trained on vast quantities of general purpose data resulting in bias, inconsistency, and and lack of domain-specific knowledge or cultural awareness. For example, generative chatbots have been accused of greenwashing fossil fuel companies role in climate change (Global Witness, 2025). These issues are addressed through ‘fine-tuning’ (additional language training with domain specific information) and ‘grounding’ (truthing against external knowledge sources including databases and knowledge graphs). Retrieval Augmented Generation (RAG) is the primary technique for grounding. Ultimately, all chatbot output should be ‘fact checked’.

LLM comparisons include:

• AI-Pro A Comprehensive Comparison of All LLMs (2024).
• mindsdb A Comparative Analysis of Leading Large Language Models (2025).
• lmarena Leaderboard compares how leading models stack up across text, image, vision, and beyond.
• Celik, et al. (2025) – Comparison of Large Language Models (LLM). UAKK 2024 The International Open Source Conference.

LLM output depends on the input ‘prompt’. Prompt engineering is the art of writing a prompt to to obtain the most appropriate output, and to better understand the capabilities and limitations of large language models. While prompt engineering will help you get the best out an LLM, but their ‘best’ must be checked for accuracy and may not be sufficient to meet use needs. For example, “Not long ago it seemed that ‘prompt engineering’ would replace CS [computer scientists]. Today, however, there are virtually no job postings for prompt engineers, while companies like LinkedIn report that the responsibilities of CS professionals have actually expanded.” (Sidu, The Conversation 2025).

For academic and research purposes you are probably better using an LLM ‘tuned’ to scientific and humanities ‘norms’, for example, one that is trained on domain specific information prioritises grounding, and limits hallucination. Specialist LLM include:

• Erasmus.ai ClimateGPT (Thulke, D. et al. 2024) is designed to enhance human decision making by offering robust climate information to researchers, policymakers, and business leaders.
• UNEP Environment GPT aims to translate environmental science into understandable information (access seem restricted).
• ICC-gpt is an interface to help you understand the latest climate change report from the Intergovernmental Panel on Climate Change (IPCC). You can ask question about the report and get answers from our AI.
• ChatClimate is grounded on the latest IPCC Report with the aim of making Climate Risk understandable and climate information more accessible to the broader communities.
• ChatNetZero is engineered to merge expert-level Net Zero domain knowledge with the capabilities of Large Language Models, overcoming the limitations that have made LLMs less trusted within the climate change community.
• EcoBots is a chatbot offering insights on environmental issues, eco-education, and funding for ecological initiatives.
• In the UrbanTestbeds.JR project public authorities employed artificial intelligence and storytelling to co-create, together with the youth, climate and sustainability plans for urban spaces.
• AgriBot is an Intelligent Chatbot For Farmers With Crop And Disease Prediction.
• AgroLLM is an AI-powered chatbot designed to enhance knowledge-sharing and education in agriculture using Large Language Models.
• AI Chatbots for Sustainable Supply Chain Collaboration and Partnerships (Akinyele and Oluwasegun, 2024).
• Robofy Sustainable Product Inquiry Chatbot.

AI/ML viewers

• Climate TRACE leverages AI to enhance the accuracy and transparency of global
  GHG emissions inventories.
• Arc-X is an interactive resource to help local governments effectively deliver services to their communities even as the climate changes provided by the US Environmental Protection Agency. 
• Climate Resilience Evaluation and Awareness Tool is a map app of the US EPA’s Cimate Scenarios Projection Map.
• AIRES is a research and innovation platform generating multidisciplinary scientific knowledge from human-nature interdependence to address the most complex sustainability problems on the planet. AIRES is a K.Lab implementation.
• Google Flood Forecasting combines two AI models that process diverse publicly available data sources: the Hydrologic Model forecasts the amount of water flowing in a river, and the Inundation Model predicts what areas will be affected and how high the water level will be. 
• Climate TRACE global emissions viewer and data download.
• Climate Central Coastal Risk Screening Tool uses machine learning developed CoastalDEM^® for high-accuracy digital elevation model (DEM) in coastal areas.
• HungerMap^LIVE is the World Food Programme (WFP)’s global hunger monitoring system. WFP’s Hunger Monitoring Unit in the Research, Assessment and Monitoring Division conducts real-time food security monitoring to track the latest food security trends. In areas where limited or no data is available, we use machine learning-based predictive models to estimate the food security situation.
• The Allen Coral Atlas, powered by Arizona State University, maps the world’s coral reefs and monitors their threats to provide actionable data and a shared understanding of coastal ecosystems. Combines high-resolution, seamless satellite imagery mosiacs, image processing techniques, machine learning, and object-based analysis (plus field data!), to generate globally consistent benthic and geomorphic mapping layers for shallow tropical coral reefs.
• International Crops Research Institute for the Semi-Arid Tropics new initiative leverages artificial intelligence (AI) and machine learning (ML) to deliver hyper-local insights for climate-resilient agriculture. AI Sowing App.
• Global Fishing Watch uses machine learning and satellite imagery to create the first global map of large vessel traffic and offshore infrastructure, finding a remarkable amount of activity that was previously “dark” to public monitoring systems.