Weather-Driven Predictive Models for Jassid and Thrips Infestation in Cotton Crop DOI Open Access
Rubaba Hamid Shafique, Sharzil Haris Khan,

Jihyoung Ryu

et al.

Sustainability, Journal Year: 2025, Volume and Issue: 17(7), P. 2803 - 2803

Published: March 21, 2025

Agriculture is a vital contributor to global food security but faces escalating threats from environmental fluctuations and pest incursions. Among the most prevalent destructive pests, Jassid (Amrasca biguttula) Thrips (Thrips tabaci) frequently afflict cotton, okra, other major crops, resulting in substantial yield losses worldwide. This paper integrates five machine learning (ML) models predict incidence based on key meteorological attributes, including temperature, relative humidity, wind speed, sunshine hours, evaporation. Two ensemble strategies, soft voting stacking, were evaluated enhance predictive performance. Our findings indicate that stacking yields superior results, achieving high multi-class AUC scores (0.985). To demystify underlying mechanisms of best-performing ensemble, this study employed SHapley Additive exPlanations (SHAP) quantify contributions individual weather parameters. The SHAP analysis revealed Standard Meteorological Week, evaporation, humidity consistently exert strongest influence forecasts. These insights align with biological studies highlighting role seasonality humid conditions fostering proliferation. Importantly, explainable approach bolsters practical utility AI-based solutions for integrated management (IPM), enabling stakeholders—farmers, extension agents, policymakers—to trust effectively operationalize data-driven recommendations. Future research will focus integrating real-time data satellite imagery further prediction accuracy, as well incorporating adaptive techniques refine model performance under varying climatic conditions.

Language: Английский

Global distribution and sustainable management of Asian corn borer (ACB), Ostrinia furnacalis (Lepidoptera: Crambidae): recent advancement and future prospects DOI
Arzlan Abbas, Babu Saddam, Farman Ullah

et al.

Bulletin of Entomological Research, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 16

Published: Jan. 21, 2025

Abstract The Asian corn borer (ACB), Ostrinia furnacalis (Guenée, 1854), is a serious pest of several crops, particularly destructive maize and other cereals throughout most Asia, including China, the Philippines, Indonesia, Malaysia, Thailand, Sri Lanka, India, Bangladesh, Japan, Korea, Vietnam, Laos, Myanmar, Afghanistan, Pakistan Cambodia. It has long been known as in South-east Asia invaded parts Solomon Islands, Africa certain regions Australia Russia. Consequently, worldwide efforts have increased to ensure new control strategies for O. management. In this article, we provide comprehensive review ACB covering its (i) distribution (geographic range seasonal variations), (ii) morphology ecology (taxonomy, life-history, host plants economic importance) (iii) management (which include agroecological approaches, mating disruption, integrated genetic chemical well biological control). Furthermore, conclude with recommendations some suggestions improving eco-friendly enhance sustainable infested areas.

Language: Английский

Citations

1
Weather-Driven Predictive Models for Jassid and Thrips Infestation in Cotton Crop DOI Open Access
Rubaba Hamid Shafique, Sharzil Haris Khan,

Jihyoung Ryu

et al.

Sustainability, Journal Year: 2025, Volume and Issue: 17(7), P. 2803 - 2803

Published: March 21, 2025

Agriculture is a vital contributor to global food security but faces escalating threats from environmental fluctuations and pest incursions. Among the most prevalent destructive pests, Jassid (Amrasca biguttula) Thrips (Thrips tabaci) frequently afflict cotton, okra, other major crops, resulting in substantial yield losses worldwide. This paper integrates five machine learning (ML) models predict incidence based on key meteorological attributes, including temperature, relative humidity, wind speed, sunshine hours, evaporation. Two ensemble strategies, soft voting stacking, were evaluated enhance predictive performance. Our findings indicate that stacking yields superior results, achieving high multi-class AUC scores (0.985). To demystify underlying mechanisms of best-performing ensemble, this study employed SHapley Additive exPlanations (SHAP) quantify contributions individual weather parameters. The SHAP analysis revealed Standard Meteorological Week, evaporation, humidity consistently exert strongest influence forecasts. These insights align with biological studies highlighting role seasonality humid conditions fostering proliferation. Importantly, explainable approach bolsters practical utility AI-based solutions for integrated management (IPM), enabling stakeholders—farmers, extension agents, policymakers—to trust effectively operationalize data-driven recommendations. Future research will focus integrating real-time data satellite imagery further prediction accuracy, as well incorporating adaptive techniques refine model performance under varying climatic conditions.

Language: Английский

Citations

0