EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Soil-Aware Hybrid AI Model for Precision Crop Recommendation and Yield Forecasting

Shilpa Mangesh Pande, Prem Kumar Ramesh

Engineering, Technology & Applied Science Research · 06.06.2026 · 16 (3) · 36190-36199

DOI: 10.48084/etasr.17876 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 06.06.2026. Verfasst von Shilpa Mangesh Pande und 1 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Matching crops to their specific soil type remains a major challenge for Indian farmers. This study proposes a model that uses crop yield, soil, and climatic data to guide optimal crop selection, improving productivity and lowering errors. Relevant environmental factors are identified through feature engineering to enhance yield prediction accuracy using the Sequential Forward Feature Selection Algorithm (SFFSA), Random Forest Variable Importance Algorithm (RFVIA), and Sequential Back Elimination Feature Selection Algorithm (SBEFSA). This study predicts the best crop to grow given a specific set of environmental conditions by employing a Machine Learning (ML) approach. A unified AI-enabled framework is created to help Indian farmers select the optimal crop to cultivate and project the Crop Yield (CY) using a hybrid system that combines Artificial Neural Network (ANN) and Multiple Linear Regression (MLR). This proposed approach employs a residual learning framework that separates linear agronomic effects from nonlinear interactions. ANN performs hyperparameter sensitivity analysis to assess the impact of learning rate and hidden neuron count to validate the performance. The results indicate that the Hybrid algorithm approach outperforms standard ML algorithms, with improvements up to 2.2-fold in RMSE and around 1.5-fold in MAE. The proposed work even predicts the best-suited fertilizer to grow the crops based on soil contents.

Zitieren

APA

Pande, S. M., & Ramesh, P. K. (2026). A Soil-Aware Hybrid AI Model for Precision Crop Recommendation and Yield Forecasting. Engineering, Technology & Applied Science Research, 16(3), 36190-36199. https://doi.org/10.48084/etasr.17876

Vancouver

Pande SM, Ramesh PK. A Soil-Aware Hybrid AI Model for Precision Crop Recommendation and Yield Forecasting. Engineering, Technology & Applied Science Research. 2026;16(3):36190-36199. doi:10.48084/etasr.17876

BibTeX
@article{Pande2026,
  author = {Pande, Shilpa Mangesh and Ramesh, Prem Kumar},
  title = {A Soil-Aware Hybrid AI Model for Precision Crop Recommendation and Yield Forecasting},
  journal = {Engineering, Technology & Applied Science Research},
  year = {2026},
  volume = {16},
  number = {3},
  pages = {36190--36199},
  doi = {10.48084/etasr.17876}
}
Kostenlos starten →