Gaia-AgStream: An Explainable AI Platform for Mining Complex Data Streams in Agriculture

Jan Schoenke , Nils Aschenbruck (1) , Roberto Interdonato (2, 3) , Rushed Kanawati (4, 5) , Ann-Christin Meisener , Francois Thierart , Guillaume Vial (6) , Martin Atzmueller (7, 1)

1 Universität Osnabrück - Osnabrück University
2 UMR TETIS - Territoires, Environnement, Télédétection et Information Spatiale
3 Cirad-ES - Département Environnements et Sociétés
4 LIPN - Laboratoire d'Informatique de Paris-Nord
5 Université Sorbonne Paris Nord 581146 - 99, avenue Jean-Baptiste Clément, 93430 Villetaneuse - France
6 LBFA - Laboratory of Fundamental and Applied Bioenergetics = Laboratoire de bioénergétique fondamentale et appliquée
7 Knowledge and Data Engineering Group

We present a position paper about our concept for an artificial intelligence (AI) and data streaming platform for the agricultural sector. The goal of our project is to support agroecology in terms of carbon farming and biodiversity protection by providing an AI and data streaming platform called Gaia-AgStream that accelerates the adoption of AI in agriculture and is directly usable by farmers as well as agricultural companies in general. The technical innovations we propose focus on smart sensor networks, unified uncertainty management, explainable AI, root cause analysis and hybrid AI approaches. Our AI and data streaming platform concept contributes to the European open data infrastructure project Gaia-X in terms of interoperability for data and AI models as well as data sovereignty and AI infrastructure. Our envisioned platform and the developed AI components for carbon farming and biodiversity will enable farmers to adopt sustainable and resilient production methods while establishing new and diverse revenue streams by monetizing carbon sequestration and AI ready data streams. The open and federated platform concept allows to bring together research, industry, agricultural start-ups and farmers in order to form sustainable innovation networks. We describe core concepts and architecture of our proposed approach in these contexts, outline practical use cases for our platform and finally outline challenges and future prospects.

Mots clés: Data Quality; Explainable AI; Sensor Networks; Distributed Systems; Uncertainty Management; Machine Learning; Complex Networks; Anomaly Detection; Root Cause Analysis; Knowledge Graph; Data Fusion; Biodiversity; Carbon Farming; Agroecology

Domaines: Intelligence artificielle [cs.AI]; Réseaux sociaux et d'information [cs.SI]; Apprentissage [cs.LG]

Jan Schoenke, Nils Aschenbruck, Roberto Interdonato, Rushed Kanawati, Ann-Christin Meisener, et al.. Gaia-AgStream: An Explainable AI Platform for Mining Complex Data Streams in Agriculture. International Conference on Smart and Sustainable Agriculture,, Jun 2021, On-line, France. pp.71-83. ⟨hal-03636208⟩