Open Access

ARTICLE

Forecasting Modeling Tool of Crop Diseases across Multiple Scenarios: System Design, Implementation, and Applications

Mintao Xu^1,#, Zichao Jin^1,#, Yangyang Tian¹, Jingcheng Zhang^1,*, Huiqin Ma¹, Yujin Jing¹, Jiangxing Wu², Jing Zhai²

1 College of Artificial Intelligence, Hangzhou Dianzi University, Hangzhou, 310018, China
2 Agricultural Technology Extension Station of Ningbo, Ningbo, 315012, China

* Corresponding Author: Jingcheng Zhang. Email:
# These authors contributed equally to this work

(This article belongs to the Special Issue: Application of Digital Agriculture and Machine Learning Technologies in Crop Production)

Phyton-International Journal of Experimental Botany 2025, 94(12), 4059-4078. https://doi.org/10.32604/phyton.2025.074422

Received 10 October 2025; Accepted 22 December 2025; Issue published 29 December 2025

Abstract

The frequent outbreaks of crop diseases pose a serious threat to global agricultural production and food security. Data-driven forecasting models have emerged as an effective approach to support early warning and management, yet the lack of user-friendly tools for model development remains a major bottleneck. This study presents the Multi-Scenario Crop Disease Forecasting Modeling System (MSDFS), an open-source platform that enables end-to-end model construction-from multi-source data ingestion and feature engineering to training, evaluation, and deployment-across four representative scenarios: static point-based, static grid-based, dynamic point-based, and dynamic grid-based. Unlike conventional frameworks, MSDFS emphasizes modeling flexibility, allowing users to build, compare, and interpret diverse forecasting approaches within a unified workflow. A notable feature of the system is the integration of a weather scenario generator, which facilitates comprehensive testing of model performance and adaptability under extreme climatic conditions. Case studies corresponding to the four scenarios were used to validate the system, with overall accuracy (OA) ranging from 73% to 93%. By lowering technical barriers, the system is designed to serve plant protection managers and agricultural producers without advanced programming expertise, providing a practical modeling tool that supports the construction of smart plant protection systems.

---

Keywords

---