Predicting rice yield and impact of climate change on rice production using machine learning models - Research

Aug 5, 2026

Upload by Aurelia

Climate change threatens agricultural sustainability and global food supply, with rice among the most climate-sensitive staples due to its dependence on temperature and rainfall. This study combines historical climate data, rice yield observations, and Global Climate Model projections (GCMs; CMIP3) to quantify impacts in Punjab, Pakistan. Multiple machine learning models (MLR, BTR, PNN, GFF, LR, and MLP) are trained on 1990–2020 data and used to project yields to 2050 under IPCC emission scenarios. Results show MLP provides the strongest performance and indicate maximum temperature as the key driver, with an estimated average yield decline of 0.12% by 2050.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages26

Reading Time1 h 6 min

AccessFree to download

Abstract

Methods and Data

Model Training and Validation

Future Projections Under IPCC Scenarios

Model Evaluation and Key Drivers

Implications for Adaptation Strategies

This document is downloaded from the VTT Research Information Portal [https://cris.vtt.fi](https://cris.vtt.fi) VTT Technical Research Centre of Finland Predicting rice yield and impact of climate change on rice production using machine learning models Tasneem, Khawaja T. ; Shahzad, Muhammad Umair; Rashid, Javed; Othman, Kamal M. ; Zafar, Tania; Faheem, Muhammad Published in: Theoretical and Applied Climatology DOI: 10.1007/s00704-025-05912-2 Published: 01/12/2025 Document Version Publisher's final version License CC BY Link to publication Please cite the original version: Tasneem, KT. , Shahzad, MU. , Rashid, J. , Othman, KM. , Zafar, T. , & Faheem, M. (2025) . Predicting rice yield and impact of climate change on rice production using machine learning models. Theoretical and Applied Climatology, 156(12), Article 665. [https://doi.org/10.1007/s00704-025-05912-2](https://doi.org/10.1007/s00704-025-05912-2) VTT [https://www.vttresearch.com](https://www.vttresearch.com) VTT Technical Research Centre of Finland Ltd [P.O. box 1000](P.O. box 1000)[ ](P.O. box 1000)[FI-02044 VTT](FI-02044 VTT)[ ](FI-02044 VTT)Finland By using VTT Research Information Portal you are bound by the following Terms & Conditions. I have read and I understand the following statement: This document is protected by copyright and other intellectual property rights, and duplication or sale of all or part of any of this document is not permitted, except duplication for research use or educational purposes in electronic or print form. You must obtain permission for any other use. Electronic or print copies may not be offered for sale. Download date: 04. Aug. 2026 Theoretical and Applied Climatology (2025) 156:665 [https://doi.org/10.1007/s00704-025-05912-2](https://doi.org/10.1007/s00704-025-05912-2) RESEARCH Predicting rice yield and impact of climate change on rice production using machine learning models Khawaja T. Tasneem1 · Muhammad Umair Shahzad2,3 · Javed Rashid4 · Kamal M. Othman5 · Tania Zafar2 · Muhammad Faheem6 Received: 7 August 2025 / Accepted: 13 November 2025 © The Author(s) 2025 Abstract Climate change poses a critical threat to agricultural sustainability, with direct implications for the global food supply. Rice, a staple crop throughout Asia, is particularly vulnerable to variations in temperature and rainfall, making it essential to understand how it responds to changing climatic conditions. This study integrates historical climate records, rice yield data, and projections from Global Climate Models (GCMs; CMIP3) to assess the potential effects of climate change on rice production in Punjab, Pakistan. We employed multiple machine learning approaches, including Multiple Linear Regression (MLR), Boosted Tree Regression (BTR), Probabilistic Neural Network (PNN), Generalized Feed-Forward (GFF) Neural Network, Linear Regression (LR), and a Multilayer Perceptron (MLP) Artificial Neural Network. The models were trained and validated using observed climate and yield data from 1990 to 2020. Future yields were projected under three IPCC emission scenarios (SR-A2, SR-A1B, SR-B1) through the year 2050. Model evaluation showed that the Multilayer Perceptron (MLP) achieved the highest predictive performance (R2 = 0.791, R = 0. 868, MAE = 0.215, MSE = 0.0869, NMSE = 0.3681), followed by Boosted Tree Regression (BTR; R2 = 0.779, R = 0. 845, MAE = 0.334, MSE = 0.1308) . The Probabilistic Neural Network (PNN) and Generalized Feed-Forward (GFF) model also performed respectably (R2 = 0.745, R = 0. 811, MAE = 0. 176, MSE = 0.380 and R2 = 0.643, R = 0. 825, MAE = 0.398, MSE = 0. 178, respectively) . In contrast, Multiple Linear Regression (MLR) and Linear Regression (LR) performed poorly, with low R2 values (0.535), underscoring their inability to capture the non-linear relationships between climate variables and yield. Our analysis identifies maximum temperature as the primary climatic driver of yield

FAQs

Which climate factor is identified as the primary driver of rice yield loss?

Maximum temperature is identified as the primary climatic driver of yield loss in the study’s analysis.

Which machine learning model achieved the highest predictive performance?

The Multilayer Perceptron (MLP) achieved the highest predictive performance, with R2 = 0.791 and R = 0.868.

How were future rice yields projected, and to what time horizon?

Future yields were projected to the year 2050 using three IPCC emission scenarios (SR-A2, SR-A1B, SR-B1) based on GCM projections.

Aug 5, 2026

Upload by Aurelia