EUVIMEDEUVIMED entdecken
Crossref

AI Driven Spatio-Temporal Modeling for Climate-Resilient Crop Yield Prediction in Indian Agro Ecosystems

Gupta, Dr. Sandeep, Hamid, Abu Bakar Abdul, Nyamasvisva, Dr.Tadiwa Elisha, Rastogi, Dr. Ritesh, Singh, Abhishek, Awasthi, Dr. Satya Prakash

Knowledge Commons (Lakehead University) · 03.12.2025

DOI: 10.17613/v67qb-fts78 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Knowledge Commons (Lakehead University), erschienen am 03.12.2025. Verfasst von Gupta und 11 weiteren Autor:innen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Climate variability and extreme weather events are increasingly disrupting agricultural productivity across India, posing a significant threat to food security and farmer livelihoods. This study develops an AI-driven spatio-temporal modeling framework for climate-resilient crop yield prediction in Indian agro-ecosystems, integrating machine learning, remote sensing, and environmental datasets. Using multi-source data such as MODIS satellite imagery, IMD climate records, soil health cards, and ground yield data the model employs Long Short-Term Memory (LSTM) and Random Forest Regression to capture temporal dependencies and spatial heterogeneity in crop response. The proposed framework was tested across three major agro-climatic zones Punjab, Maharashtra, and Tamil Nadu covering both irrigated and rain-fed systems. Results show that the AI-based ensemble achieved superior prediction accuracy (R² = 0.91; RMSE = 0.38 t/ha) compared to traditional regression approaches. The model effectively identified climate-sensitive yield hotspots and revealed that temperature anomalies and soil moisture deficits were the most critical predictors of yield decline. This research demonstrates how artificial intelligence combined with geospatial analytics can enable real-time, scalable, and data-driven decision support for climate-resilient agriculture, providing actionable insights for policymakers and farmers to mitigate climate risks and optimize resource allocation.

Schlagwörter

crop yield predictionclimate resiliencespatio-temporal modelingLSTMrandom forest regressionensemble learningMODIS imagerysoil water deficittemperature anomaliesdecision support for farmers

Zitieren

APA

Gupta, Sandeep, D., Hamid, Abdul, A. B., Nyamasvisva, Elisha, D., Rastogi, Ritesh, D., Singh, Abhishek, Awasthi, & Prakash, D. S. (2025). AI Driven Spatio-Temporal Modeling for Climate-Resilient Crop Yield Prediction in Indian Agro Ecosystems. Knowledge Commons (Lakehead University). https://doi.org/10.17613/v67qb-fts78

Vancouver

Gupta, Sandeep D, Hamid, Abdul AB, Nyamasvisva, Elisha D, et al. AI Driven Spatio-Temporal Modeling for Climate-Resilient Crop Yield Prediction in Indian Agro Ecosystems. Knowledge Commons (Lakehead University). 2025. doi:10.17613/v67qb-fts78

BibTeX
@article{Gupta2025,
  author = {Gupta and Sandeep, Dr. and Hamid and Abdul, Abu Bakar and Nyamasvisva and Elisha, Dr.Tadiwa and Rastogi and Ritesh, Dr. and Singh and Abhishek and Awasthi and Prakash, Dr. Satya},
  title = {AI Driven Spatio-Temporal Modeling for Climate-Resilient Crop Yield Prediction in Indian Agro Ecosystems},
  journal = {Knowledge Commons (Lakehead University)},
  year = {2025},
  doi = {10.17613/v67qb-fts78}
}
Kostenlos starten →