Temporal dynamics of sapota pest damage and Phytophthora disease: insights from time series and machine learning models

Aug 5, 2026

Temporal variability in sapota (Manilkara zapota) pest damage and Phytophthora disease is examined to clarify how climate shapes long-term biotic stress patterns. A decade-long dataset from major sapota-growing districts in Maharashtra (2014–2022) is analyzed using statistical and machine learning time-series methods including ARIMA, SARIMA, and VAR, supplemented by Random Forest feature-importance evaluation and correlation analyses. Forecasting performance and driver relationships are quantified, revealing distinct roles of rainfall, temperature extremes, humidity, and minimum temperature in shaping bud borer, seed borer, and disease severity.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Methods

Results

Discussion

Keywords

TYPE Original Research PUBLISHED 23 September 2025 DOI 10.3389/fpls.2025.1659709 OPEN ACCESS EDITED BY Xiao Ming Zhang, Yunnan Agricultural University, China REVIEWED BY Balaji Bn, National Bureau of Agricultural Insects Resources, India Ivan Malashin, Bauman Moscow State Technical University, Russia *CORRESPONDENCE Meenakshi Malik [minaxi.2007@gmail.com](minaxi.2007@gmail.com)[ ](minaxi.2007@gmail.com)Niranjan Singh [attri.ns@gmail.com](attri.ns@gmail.com)[ ](attri.ns@gmail.com)Amoghavarsha Chittaragi [amoghchittaragi@gmail.com](amoghchittaragi@gmail.com) RECEIVED 07 July 2025 ACCEPTED 14 August 2025 PUBLISHED 23 September 2025 CITATION Malik M, Singh N, Chittaragi A, D R, Patil B and Manisha BL (2025) Temporal dynamics of sapota pest damage and Phytophthora disease: insights from time series and machine learning models. Front. Plant Sci. 16:1659709 . doi: 10.3389/fpls.2025.1659709 COPYRIGHT © 2025 Malik, Singh, Chittaragi, D, Patil and Manisha. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Temporal dynamics of sapota pest damage and Phytophthora disease: insights from time series and machine learning models Meenakshi Malik 1*, Niranjan Singh 2*, Amoghavarsha Chittaragi 3*, Raghavendra D 4, Balanagouda Patil 5 and Bachu Lakshmi Manisha 4 1Agricultural Statistics, Indian Council of Agricultural Research (ICAR)-National Research Institute for Integrated Pest Management, New Delhi, India, 2Computer Applications, ICAR-National Research Institute for Integrated Pest Management, New Delhi, India, 3 ICAR-KVK, Chintamani, University of Agricultural Sciences, GKVK, Bangalore, India, 4 Entomology, ICAR-National Research Institute for Integrated Pest Management, New Delhi, India, 5 Plant Pathology, Keladi Shivappa Nayaka University of Agricultural and Horticultural Sciences, Iruvakki, Sagar, India Introduction: Sapota (Manilkara zapota L.) is a major tropical fruit crop prone to damage by bud borer (Anarsia achrasella), seed borer (Trymalitis margarias), and fruit rot caused by Phytophthora species. Climatic variability strongly inﬂuences these biotic stresses, yet long-term temporal patterns remain poorly quantiﬁed. Methods: A decade-long dataset (2014–2022) from 21 major sapota-growing districts of Maharashtra, India, was analyzed to study pest and disease dynamics. Statistical and machine learning approaches, including ARIMA, SARIMA, and VAR time-series models, along with Random Forest feature importance analysis, were applied to quantify climatic inﬂuences and forecast severity trends. Correlation analyses were used to assess weather–pest/disease associations. Results: Trend analysis revealed ﬂuctuating bud and seed borer damage, while Phytophthora disease severity remained relatively stable. Bud borer incidence was positively correlated with rainfall (r = 0.69), seed borer with maximum temperature (r =0 .47), and Phytophthora with minimum temperature (r = 0 .64) . The ARIMA model provided accurate forecasts for bud borer (MSE = 8 . 03) and Phytophthora (MSE = 0.20), while the VAR model performed best for seed borer (MSE = 17 .96) . Random Forest analysis identiﬁed minimum temperature as the most critical driver of bud borer and Phytophthora severity, whereas relative humidity was most inﬂuential for seed borer. Discussion: The integration of statistical and machine learning models provides robust insights into sapota pest and disease epidemiology under climatic variability. These ﬁndings highlight the importance of temperature, humidity, and rainfall in shaping pest–pathogen

FAQs

What sapota pests and disease are studied in the paper?

The study focuses on bud borer and seed borer damage and Phytophthora-caused fruit rot disease affecting sapota cultivation.

Which data and locations are used for the analysis?

A decade-long dataset from 21 major sapota-growing districts of Maharashtra, India, covering 2014–2022, is used to quantify temporal dynamics.

How do ARIMA, SARIMA, and VAR models contribute to the findings?

These time-series models are used to forecast severity trends for bud borer, seed borer, and Phytophthora, with model performance assessed by mean squared error.

Aug 5, 2026

Upload by Genevieve