Early Detection of Branched Broomrape (Phelipanche ramosa) Infestation in Tomato Crops Using Leaf Spectral Analysis and Machine Learning

2025-09-15

AI Summary

Phelipanche ramosa, a parasitic broomrape, poses a critical early asymptomatic threat to tomato crops, with symptoms remaining undetectable until advanced infection stages. Method: This study develops a proximal spectral sensing and ensemble machine learning framework for pre-symptomatic detection. Leaf reflectance spectra (400–2500 nm) are acquired and integrated with growing degree days (GDD) to dynamically assess infection progression. A novel ensemble of four classifiers—Random Forest, XGBoost, RBF-SVM, and Naïve Bayes—is employed for early parasitism identification. Spectral preprocessing includes denoising, 1-nm interpolation, Savitzky-Golay smoothing, and correlation-based band selection. Results: Distinct spectral divergence is observed near 1500 nm and 2000 nm. At 1500 GDD (~585 accumulated GDD post-infection), the model achieves 89% overall accuracy (infection-class recall = 0.86; healthy-class recall = 0.93), significantly preceding canopy-level symptom emergence. This demonstrates the method’s feasibility and advancement for real-time, field-deployable early warning of P. ramosa infestation.

Technology Category

Machine Learning: Ensemble MethodsIntelligent Robots: Multimodal Perception & Sensor FusionSearch and Optimization: Mixed Discrete/Continuous Search

Application Category

Web Mining and Content Analysis: Robustness and generalizability of Web mining methodsSearch and Retrieval-Augmented AI: Web evaluation methodologies and metricsSystems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Branched broomrape (Phelipanche ramosa) is a chlorophyll-deficient parasitic weed that threatens tomato production by extracting nutrients from the host. We investigate early detection using leaf-level spectral reflectance (400-2500 nm) and ensemble machine learning. In a field experiment in Woodland, California, we tracked 300 tomato plants across growth stages defined by growing degree days (GDD). Leaf reflectance was acquired with a portable spectrometer and preprocessed (band denoising, 1 nm interpolation, Savitzky-Golay smoothing, correlation-based band reduction). Clear class differences were observed near 1500 nm and 2000 nm water absorption features, consistent with reduced leaf water content in infected plants at early stages. An ensemble combining Random Forest, XGBoost, SVM with RBF kernel, and Naive Bayes achieved 89% accuracy at 585 GDD, with recalls of 0.86 (infected) and 0.93 (noninfected). Accuracy declined at later stages (e.g., 69% at 1568 GDD), likely due to senescence and weed interference. Despite the small number of infected plants and environmental confounders, results show that proximal sensing with ensemble learning enables timely detection of broomrape before canopy symptoms are visible, supporting targeted interventions and reduced yield losses.

Problem

• Early detection of parasitic weed infestation in tomato crops
• Using leaf spectral analysis for identifying broomrape infection
• Applying machine learning to enable timely intervention before visible symptoms

Innovation

• Leaf spectral reflectance analysis
• Ensemble machine learning models
• Early detection via water absorption features