Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 23, 2026Discover ComputingOpen Access

Explainable multi season spatio temporal deep learning framework for crop yield forecasting using sentinel 2 remote sensing data

View Full Paper
Ask AI
Bookmark
Share

Authors

YGYedukondalu GamidellMCMousmi Ajay Chaurasia

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved crop yield forecasting in agriculture, indicating potential for enhanced decision-making.

Key Points

  • The research aims to develop an explainable deep learning framework for accurate crop yield forecasting using multi-season spectral data.
  • Introduced YieldFusionAI, a multi-season spatiotemporal deep learning model.
  • Integrated CNNs and Bi-LSTM networks with attention mechanisms for modeling temporal dynamics.
  • Employed vegetation indices and implemented a calibration module for improved prediction reliability.
  • Achieved an RMSE of 0.273 t ha⁻¹ and MAE of 0.213 t ha⁻¹.
  • Reported an R² of 0.894 and MAPE of 6.82%.
  • Outperformed conventional machine learning and deep learning baselines.

Cite This Study

Gamidell et al. (2026) studied this question.

synapsesocial.com/papers/6a61aea0faa9903c51169d28https://doi.org/10.1007/s10791-026-10375-8
View Full Paper
Ask AI
Bookmark
Share