Multi-source temporal fusion and multi-station learning for early warning of diamondback moth infestation in Brassica crops
- 1School of Information Management, Sun Yat-sen University, Guangzhou, Guangdong, China
- 2Institute of Quality Standard and Monitoring Technology for Agro-products of Guangdong Academy of Agricultural Sciences, Guangzhou, China
Abstract
Introduction: Meteorological variability influences diamondback moth (DBM; Plutella xylostella) infestation and the resulting damage to Brassica crops. Accurate multi-horizon forecasting requires models that preserve short-lived meteorological exposures while integrating thermal timing, spatial dependence, and recent infestation dynamics within a transparent framework.
Methods: The Temporal–Geospatial Pest Network (TG-PestNet) forecasts the weekly percentage of inspected plants classified as DBM-infested 1 to 4 weeks ahead at four Guangdong stations, from origin-time information only. It preserves hourly exposure, encodes lookback weeks on a thermal-time axis, couples stations through a wind-informed graph, and protects infestation history in a gated anchor. Evaluation used 344 synchronized weeks, 66 later test origins, 13 history-only comparators, retraining ablations, matched-width controls, and input-matched generic encoders.
Results and discussion: TG-PestNet achieved the lowest observed root-mean-square error, mean absolute error, and mean absolute percentage error in all 12 station–metric combinations, with mean reductions of 5.9%–13.0%. Year-ahead forecasts outperformed persistence in all four test years. Removing the history anchor increased error by 14.3% and remained significant after multiplicity correction, demonstrating its central contribution to forecast accuracy. Meteorological information provided complementary predictive value: its occlusion increased the error by 9.3%, and retraining without it increased the macro RMSE by 3.6%. TG-PestNet also substantially outperformed the two input-matched generic encoders, whose errors were approximately one quarter higher. These results establish TG-PestNet as an accurate, reproducible and auditable framework for multi-station pest forecasting, with component-level analyses that identify the dominant contribution of recent infestation history and characterize the predictive roles of high-resolution meteorology and structured spatial information.
Related
- Epicuticular Wax Composition and Wax Crystal Microstructure Shape Oviposition Preference in the Diamondback Moth, Plutella xylostella, on Cabbage.
- Conservation Implications of High Population Genetic Structure Detected in a Parasitic Fluke of Diamondback Terrapins
- Early Detection of Red Palm Weevil Infestation: A Systematic Review of Sensing Technologies, Artificial Intelligence, and Field Readiness
- Dolycoris baccarum (L.) (Hemiptera: Pentatomidae) Infestation Induced Differential Changes in Plant Physiology: Preference and Damaging Nature to Different Sesame (Sesamum indicum L.) Varieties
- Physics-guided explainable machine learning for predicting temporal scour evolution around hybrid spur dikes under unsteady flood hydrographs
BibTeX
@article{zhang2026multisource,
title = {{Multi-source temporal fusion and multi-station learning for early warning of diamondback moth infestation in Brassica crops}},
author = {Dong Zhang and Jiale Wang},
journal = {Frontiers in Plant Science},
year = {2026},
month = oct,
doi = {10.3389/fpls.2026.1953590},
url = {https://doi.org/10.3389/fpls.2026.1953590},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Multi-source temporal fusion and multi-station learning for early warning of diamondback moth infestation in Brassica crops
AU - Dong Zhang
AU - Jiale Wang
PY - 2026
DA - 2026/10/12
JO - Frontiers in Plant Science
DO - 10.3389/fpls.2026.1953590
UR - https://doi.org/10.3389/fpls.2026.1953590
AB - Introduction: Meteorological variability influences diamondback moth (DBM; Plutella xylostella) infestation and the resulting damage to Brassica crops. Accurate multi-horizon forecasting requires models that preserve short-lived meteorological exposures while integrating thermal timing, spatial dependence, and recent infestation dynamics within a transparent framework. Methods: The Temporal–Geospatial Pest Network (TG-PestNet) forecasts the weekly percentage of inspected plants classified as DBM-infested 1 to 4 weeks ahead at four Guangdong stations, from origin-time information only. It preserves hourly exposure, encodes lookback weeks on a thermal-time axis, couples stations through a wind-informed graph, and protects infestation history in a gated anchor. Evaluation used 344 synchronized weeks, 66 later test origins, 13 history-only comparators, retraining ablations, matched-width controls, and input-matched generic encoders. Results and discussion: TG-PestNet achieved the lowest observed root-mean-square error, mean absolute error, and mean absolute percentage error in all 12 station–metric combinations, with mean reductions of 5.9%–13.0%. Year-ahead forecasts outperformed persistence in all four test years. Removing the history anchor increased error by 14.3% and remained significant after multiplicity correction, demonstrating its central contribution to forecast accuracy. Meteorological information provided complementary predictive value: its occlusion increased the error by 9.3%, and retraining without it increased the macro RMSE by 3.6%. TG-PestNet also substantially outperformed the two input-matched generic encoders, whose errors were approximately one quarter higher. These results establish TG-PestNet as an accurate, reproducible and auditable framework for multi-station pest forecasting, with component-level analyses that identify the dominant contribution of recent infestation history and characterize the predictive roles of high-resolution meteorology and structured spatial information.
SN - 1664-462X
ER -