Technology Category
Computer Vision: Remote Sensing / Geospatial AIData Mining & Knowledge Management: Knowledge Acquisition from the WebIntelligent Robots: Multimodal Perception & Sensor Fusion
Branched Broomrape Detection in Tomato Farms Using Satellite Imagery and Time-Series Analysis
🤖 AI Summary
Striga hermonthica, a devastating subterranean parasitic weed, causes up to 80% yield loss in tomato production; its cryptic growth habit and persistent seed bank (up to 200,000 seeds per plant, viable for two decades) necessitate early remote sensing detection. This study proposes an end-to-end detection framework integrating Sentinel-2 time-series imagery with multi-source features. It innovatively combines neural-network-based inversion of functional plant parameters—such as canopy chlorophyll content (CCC) and leaf area index (LAI)—with LSTM-based temporal modeling, while incorporating a growing-degree-day model to harmonize phenological baselines and enhance temporal consistency of stress responses. Permutation importance analysis identifies the normalized difference moisture index (NDMI) and CCC as the most sensitive indicators. Evaluated on tomato fields in California, the model achieves 88% accuracy on training data and 87% on independent test data, with an F1-score of 0.89. Results demonstrate the efficacy and practicality of satellite-driven time-series methods for large-scale, early detection of parasitic weeds.
Technology Category
Application Category
📝 Abstract
Branched broomrape (Phelipanche ramosa (L.) Pomel) is a chlorophyll-deficient parasitic plant that threatens tomato production by extracting nutrients from the host, with reported yield losses up to 80 percent. Its mostly subterranean life cycle and prolific seed production (more than 200,000 seeds per plant, viable for up to 20 years) make early detection essential. We present an end-to-end pipeline that uses Sentinel-2 imagery and time-series analysis to identify broomrape-infested tomato fields in California. Regions of interest were defined from farmer-reported infestations, and images with less than 10 percent cloud cover were retained. We processed 12 spectral bands and sun-sensor geometry, computed 20 vegetation indices (e.g., NDVI, NDMI), and derived five plant traits (Leaf Area Index, Leaf Chlorophyll Content, Canopy Chlorophyll Content, Fraction of Absorbed Photosynthetically Active Radiation, and Fractional Vegetation Cover) using a neural network calibrated with ground-truth and synthetic data. Trends in Canopy Chlorophyll Content delineated transplanting-to-harvest periods, and phenology was aligned using growing degree days. Vegetation pixels were segmented and used to train a Long Short-Term Memory (LSTM) network on 18,874 pixels across 48 growing-degree-day time points. The model achieved 88 percent training accuracy and 87 percent test accuracy, with precision 0.86, recall 0.92, and F1 0.89. Permutation feature importance ranked NDMI, Canopy Chlorophyll Content, FAPAR, and a chlorophyll red-edge index as most informative, consistent with the physiological effects of infestation. Results show the promise of satellite-driven time-series modeling for scalable detection of parasitic stress in tomato farms.
Problem
Research questions and friction points this paper is trying to address.
Detecting parasitic branched broomrape in tomato farms
Using satellite imagery and time-series analysis
Identifying infestation through chlorophyll deficiency indicators
Innovation
Methods, ideas, or system contributions that make the work stand out.
Uses Sentinel-2 satellite imagery and time-series analysis
Employs LSTM neural network on vegetation indices data
Derives plant traits through neural network processing
🔎 Similar Papers
No similar papers found.
