Fair Forward - Open Data & Use Cases

Field data collected on agricultural farm land (crops) with raw datasets + applied use cases of classification of land use cover using ML (based on individual projects presented)

The Ghana Crop Disease Detection Challenge is an online data science challenge that seeks to leverage the power of Machine Learning and Artificial Intelligence to detect diseases that attack crops and offer immediate remedies.

Using TTS models to create health-related audio messages that can be shared with civil society organizations for awareness raising and capacity building

This dataset is part of the initiative SYSPIN (SYnthesizing SPeech in INdian languages), that develops large open-source Text-to-Speech (TTS) corpora, i.e., speech training datasets and AI models in 9 Indian languages, namely – Bengali, Bhojpuri, Chhattisgarhi, Hindi, Kannada, Magahi, Maithili, Marathi, and Telugu. This data is useful for those wishing to build voice-enabled, user-friendly applications in Indian languages. Through voice-based solutions, these AI models can be used to empower communities that do not have access to digital services in their own native language. They can be used by private companies, researchers, NGOs or government departments to develop digital applications. The datasets and TTS models are available to the AI community and anyone wishing to build voice-enabled applications in Indian languages.

This AI application is about developing an AI-based system to tackle climate misinformation in Indonesia, focusing on creating accurate and accessible information tools. The initiative aims to build a multilingual disinformation detection system, covering Bahasa Indonesia and over 10,6 million words and 21 million words translation from Minangkabau, Balinese, and Buginese to classify and verify climate-related content. The application supports stakeholders, including government agencies, NGOs, and communities, in countering false narratives, promoting awareness, and enabling evidence-based decision-making. The AI outcomes include open-access datasets, disinformation, and topic classification models, a user-friendly website, and a chatbot. These tools empower users to identify climate misinformation, enhance public literacy, and foster collaboration for sustainable climate actions. The project emphasizes inclusivity, accessibility, and long-term impact, providing resources for researchers, local businesses, and policy-makers to advance AI applications in combating misinformation. Prosa has developed an AI-powered chatbot to address climate misinformation. The platform's website is available at faktaiklim.prosa.ai, and the chatbot can be accessed via Telegram (Fakta Iklim Bot), with open-source code available on GitHub. User guides are provided in four languages: Indonesian, Minangkabau, Balinese, and Bugis.

This project focuses on creating validated, open-source High Carbon Stock (HCS) forest maps for Indonesia using an AI-driven approach. It adopts the HCS classification system to identify forests suitable for conservation versus sustainable development: • High, Medium, and Low-Density Forests (Conservation Priority): Forests with closed or patchy canopies, rich biodiversity, and carbon storage. • Young Regenerating Forests: Regrowing forests that are transitioning into higher carbon stock potential. • Scrub and Open Land: Areas with minimal carbon stock suitable for sustainable development. The maps integrate field data, satellite imagery, and AI to assist policymakers, NGOs, and businesses in making data-driven decisions for sustainable land-use planning and conservation. Stakeholders can use the outputs for spatial planning, reducing greenhouse gas emissions, and implementing "no deforestation" commitments. The High Carbon Stock Approach (HCSA) project was nominated for the prestigious UN SDG Game Changer award – Category 2: Planet – Innovation for our climate and environment “Artificial Intelligence Meets Jungle/ Forest Forward.

the challenge was organized to predict biomass in shaded regions (cocoa plantations) in Cote d’Ivoire based on GEDI, Sentinel-2 and ground truth biomass data. Remote monitoring of the increase of biomass will help measure the impact of reforestation efforts in Cote d’Ivoire as well as detect degradation of forests due to cocoa, without requiring expensive and labor-intensive biomass estimates on the ground.

100 hours of Text to Speech Dataset for Mundari Language

This AI application and replication-kit is about an AI-based crop type map for Telangana. This should be of use to anyone wishing to support sustainable farming practices and evidence-based decision-making for agricultural. Also, this can be used to empower you, as a local business, and NGOs, or a government agency to develop digital agricultural applications. The application focuses on creating localized ground-truth data on several different crop related variables to train AI models tailored to Telangana's diverse agricultural landscape. This includes an open-access ground-truth dataset, a data challenge with openly available models for yield prediction, a crop classification model using satellite imagery applied to map the whole state of Telangana, and a roadmap for AI implementation in agriculture. Datasets, AI models, and crop maps are all openly available as an open-source replication kit and digital public good.

Univ of Stellenbosch Grant (Febe de Wet) - Voices of Mzansi project / localise SA local languages on Mozilla CV platform

Improve the Kahi Ankahi Baatein (KAB) platform by fine-tuning Hindi LLMs for better user experience.