Scholarlink

<p>Accurate crop yield prediction under climatic variability is fundamental to food security planning and agricultural policy. Classical statistical and machine learning approaches often struggle to handle imprecise, incomplete, or linguistically described agronomic data arising from uncertain climatic conditions. In this paper, a novel fuzzy graph-based prediction model (FGBPM) that integrates fuzzy set theory with graph-theoretic structures is proposed to model complex, nonlinear relationships between climatic parameters and crop yield outcomes. Fuzzy membership functions are constructed for temperature, rainfall, humidity, and solar radiation. A weighted fuzzy relational graph is constructed over historical agroclimate datasets (2005–2024) from five agroecological zones in India. Fuzzy inference rules, derived via expert elicitation and data-driven correlation, propagate climatic uncertainty through the graph to generate probabilistic yield distributions. The FGBPM achieves a coefficient of determination (R²) of 0.961, a root mean square error (RMSE) of 0.112 t/ha, and a mean absolute error (MAE) of 0.089 t/ha on the test set, outperforming the artificial neural network (ANN), support vector machine (SVM), random forest, and linear regression baselines. An ablation study confirms that each model component—graph-based propagation, expert rule base, and α-cut uncertainty generation—independently contributes to overall performance, with graph propagation alone accounting for a 14.2% reduction in the RMSE relative to a stand-alone fuzzy inference system. The model generates quantified uncertainty intervals for seasonal yield forecasts, demonstrated across wheat, rice, maize, and soybean crops. Compared with existing methods, the proposed FGBPM demonstrates superior predictive accuracy, interpretability, and uncertainty quantification capacity. Open-source implementation supports reproducibility and adoption by agricultural decision-support systems across diverse agroclimatic contexts.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A fuzzy graph-based prediction model for crop yield forecasting under climatic variability

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月3日

查看全文
  • S. V. B. Subrahmanyeswara Rao,
  • T. Srinivasa Rao,
  • M. Sowjanya,
  • P. Raja Sekhar

摘要

Accurate crop yield prediction under climatic variability is fundamental to food security planning and agricultural policy. Classical statistical and machine learning approaches often struggle to handle imprecise, incomplete, or linguistically described agronomic data arising from uncertain climatic conditions. In this paper, a novel fuzzy graph-based prediction model (FGBPM) that integrates fuzzy set theory with graph-theoretic structures is proposed to model complex, nonlinear relationships between climatic parameters and crop yield outcomes. Fuzzy membership functions are constructed for temperature, rainfall, humidity, and solar radiation. A weighted fuzzy relational graph is constructed over historical agroclimate datasets (2005–2024) from five agroecological zones in India. Fuzzy inference rules, derived via expert elicitation and data-driven correlation, propagate climatic uncertainty through the graph to generate probabilistic yield distributions. The FGBPM achieves a coefficient of determination (R²) of 0.961, a root mean square error (RMSE) of 0.112 t/ha, and a mean absolute error (MAE) of 0.089 t/ha on the test set, outperforming the artificial neural network (ANN), support vector machine (SVM), random forest, and linear regression baselines. An ablation study confirms that each model component—graph-based propagation, expert rule base, and α-cut uncertainty generation—independently contributes to overall performance, with graph propagation alone accounting for a 14.2% reduction in the RMSE relative to a stand-alone fuzzy inference system. The model generates quantified uncertainty intervals for seasonal yield forecasts, demonstrated across wheat, rice, maize, and soybean crops. Compared with existing methods, the proposed FGBPM demonstrates superior predictive accuracy, interpretability, and uncertainty quantification capacity. Open-source implementation supports reproducibility and adoption by agricultural decision-support systems across diverse agroclimatic contexts.