{"type":"ScholarlyArticle","title":"AG-STELLA: Spatio-Temporal Learning for Water-related Agricultural Land Use Activity Mapping with AlphaEarth","authors":[{"name":"Nibir Chandra Mandal","slug":"nibir-chandra-mandal","given":"Nibir Chandra","family":"Mandal","affiliation":""},{"name":"Oishee Bintey Hoque","slug":"oishee-bintey-hoque","given":"Oishee Bintey","family":"Hoque","affiliation":""},{"name":"Kyle Luong","slug":"kyle-luong","given":"Kyle","family":"Luong","affiliation":""},{"name":"Samarth Swarup","slug":"samarth-swarup","given":"Samarth","family":"Swarup","affiliation":""},{"name":"Kirti Rajagopalan","slug":"kirti-rajagopalan","given":"Kirti","family":"Rajagopalan","affiliation":""},{"name":"Mandy L Wilson","slug":"mandy-l-wilson","given":"Mandy L","family":"Wilson","affiliation":""},{"name":"Abhijin Adiga","slug":"abhijin-adiga","given":"Abhijin","family":"Adiga","affiliation":""},{"name":"Madhav Marathe","slug":"madhav-marathe","given":"Madhav","family":"Marathe","affiliation":""}],"abstract":"Accurate mapping of agricultural land use activity, particularly long-term transition from cropland to pasture and short-term transition between cropland to fallow land, is essential for sustainable water management, drought response, and food-system resilience which directly supports United Nations Sustainable Development Goals (SDG-2 and SDG-8). However, reliable agricultural land use activity mapping is challenging due to spectral ambiguity, temporal irregularities, severe class imbalance, and limited generalization across agricultural regions. In this work, we propose AG-STELLA, a knowledge guided spatio-temporal model that (i) captures temporal changes of agricultural lands using pretrained spatio-temporal transformers; (ii) integrates geospatial context using AlphaEarth embedding; (iii) introduces a temporal transition latent space with temporal consistency constraints; (iv) employs guidance through hydroclimatic consistency; and (v) uses a land use-aware gated decoder to improve robustness across regions. Through experimentation across three water-stressed U.S. states, we show consistent gains over baseline vision and foundation models, achieving up to 27% F1-score improvement for pasture (minority class) and 16% overall. We further show the robustness across heterogeneous regions through cross-state transfer learning, where AG-STELLA consistently outperforms foundation model baselines and achieve up to 82.3% F1-score for fallow land with a 9.6% improvement over the best foundation model. Code: https://github.com/Nibir088/AG-STELLA","doi":"10.24963/ijcai.2026/816","url":"https://ijcai.org/proceedings/2026/816","pdf":"https://ijcai.org/proceedings/2026/0816.pdf","markdown":"https://ijcai.org/proceedings/2026/816.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/816","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"AI and Social Good","track":"AI and Social Good","number":816,"pages":{"first":7337,"last":7345},"keywords":["Computer Vision: Computer Vision","Multidisciplinary Topics and Applications: Multidisciplinary Topics and Applications","Machine Learning: Machine Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}