Tarin Paz-Kagan

1. Leaf Area Index (LAI) is a key biophysical variable for understanding the structural and functional characteristics of forest ecosystems. It is the ratio of leaf surface area to ground surface a...

Purpose: Accurate spatial management units are fundamental to precision agriculture because they directly influence crop classification, input optimization, and decision-support systems. However, administrative agricultural parcels often aggregate multiple crop units within a single polygon, introducing structural uncertainty into parcel-based crop mapping and management analytics. This study addresses inaccuracies in existing agricultural parcel boundaries that introduce upstream errors that cascade into downstream analyses, including crop mapping, yield estimation, and decision-support workflows. Consequently, the proposed framework is designed for parcel refinement rather than semantic crop classification. Methods: We selected parcel refinement as a polygon-conditioned semantic segmentation problem, leveraging existing parcel geometries to generate more accurate, agronomically coherent management units rather than performing field boundary detection from scratch. Implemented at the national scale in Israel, the framework uses a computationally efficient single-sensor Sentinel-2 time-series approach based on harmonic modeling to generate phenology-aware composites that improve robustness to noise, cloud contamination, and temporal gaps. Geometry-preserving synthetic data augmentation was incorporated to improve boundary learning under limited annotations, and outputs were evaluated using both pixel-level segmentation metrics and polygon-level operational correctness. Results: We compared a zero-shot Segment Anything Model (SAM) pipeline with supervised deep learning architectures (U-Net, DeepLabV3, and SegFormer). U-Net achieved the strongest boundary performance (mean IoU = 0.76) and improved polygon-level correctness from 75.16% to 87.8% (absolute gain: 12.64% points; relative improvement: 16.8%). Conclusion: The proposed framework provides a scalable pathway to reduce structural uncertainty in agricultural parcel databases and strengthen the spatial foundation of precision agriculture and data-driven agricultural management systems.

Soil degradation can intensify abruptly during armed conflict due to heavy machinery traffic and earthworks that compact cropland soils and disrupt surface structure. We develop field-scale, remote-sensing indicators of conflict-driven soil compaction in agricultural land in the Western Negev (Israel) using the Sentinel-1 InSAR time series. Sentinel-1A IW ascending and descending acquisitions (2017-2024) were processed with LiCSAR interferograms and LiCSBAS time-series analysis to estimate line-of-sight (LOS) velocity and cumulative displacement. To isolate conflict-related impacts, the time series was analyzed in two periods: pre-war (before 7 October 2023) and post-war (from 7 October 2023 onward), treating this date as a structural change point. InSAR-derived metrics were linked to Ministry of Agriculture field and damage polygons to extract per-field velocity trends, cumulative displacement, and incremental displacement between consecutive acquisitions. Pre-war conditions were largely stable, with most fields exhibiting LOS velocities within ±2 mm yr⁻¹. Post-war maps reveal spatially coherent subsidence in reported damaged parcels, frequently exceeding -10 mm yr⁻¹ and locally reaching below -30 mm yr⁻¹, consistent with severe soil compaction and disturbance. Time series show abrupt step changes and negative displacement “shock” events after the onset of the conflict, while adjacent parcels often remain stable, highlighting strong heterogeneity at the field scale. The proposed indicator set, velocity shifts, cumulative displacement changes, and incremental deformation anomalies provide a rapid, scalable framework for screening soil degradation, prioritizing remediation, and tracking recovery trajectories in data-scarce, crisis-affected agricultural landscapes.Keywords: soil degradation, soil compaction, Sentinel-1, InSAR time series, LiCSBAS, conflict impacts, agricultural damage mapping

Accurate, timely, and spatially consistent crop maps are a cornerstone of sustainable agricultural management, climate adaptation, and evidence-based policy. Yet national-scale crop mapping remains challenging in heterogeneous agroecosystems due to fragmented field structures, dynamic land use, and the contrasting spatiotemporal characteristics of annual crops and perennial orchards. Addressing these pressures requires scalable, data-driven approaches that translate advances in Earth observation (EO), data science, and modelling into actionable tools for climate-resilient agroecosystem management. Here we present an integrated, end-to-end crop-mapping framework that synthesizes complementary methodological advances to enable robust, operational monitoring of agricultural systems across space, time, and crop types. Using Israel as a national-scale case study representative of heterogeneous, intensively and extensively managed agroecosystems, the framework links fine-scale field structure, crop phenology, and multi-year dynamics to support decision-making under climatic variability. First, national cadastral parcel layers are refined into agronomically homogeneous field units using deep learning-based semantic segmentation (U-Net, DeepLabV3, and SegFormer) and foundation models (SAM), addressing a critical limitation of registry-based agricultural databases. A U-Net architecture outperformed SegFormer and DeepLabV3, achieving a mean Intersection-over-Union (IoU) of 0.76 with balanced precision-recall. At the national scale, polygon correctness improved from 75.16% to 86.37%, resulting in tens of thousands of fields segmented into homogeneous management units. This step substantially improves geometric consistency and the reliability of downstream crop classification and agroecosystem analysis. Second, a hierarchical, multi-sensor classification strategy integrates Sentinel-1 SAR and Sentinel-2 multispectral time series with phenological metrics and expert-driven feature selection to map agricultural land use and dynamically classify annual field crops across multiple growing seasons. XGBoost achieved the highest land-cover accuracy (OA = 0.909), driven primarily by vegetation, moisture, and chlorophyll-sensitive indices (NDVI, MCARI, NDMI, PGHI). For detailed row-crop mapping, deep learning models outperformed traditional machine learning (TabM OA = 0.861). Multi-satellite fusion ensured robustness and transferability, yielding an average leave-one-year-out accuracy of 0.833. This integration captures crop rotations, seasonal shifts, and climate-driven phenological gradients, enabling consistent multi-year monitoring in dryland and Mediterranean environments. Third, perennial orchard systems, often underrepresented in national crop statistics, are mapped using a multimodal fusion approach that combines very-high-resolution (VHR) aerial imagery with multi-temporal Sentinel-1/2 data. Deep learning architectures jointly exploit fine-scale spatial structure and phenological dynamics, achieving the highest performance across all evaluation settings (same-year OA = 0.890 ± 0.009; cross-year OA = 0.881 ± 0.014), with particularly strong gains for early-stage and sparsely vegetated orchards. Overall, the framework is designed for scalability, interpretability, and operational deployment, demonstrating how multi-modal remote sensing, deep learning, and hierarchical modelling can bridge scientific innovation and real-world agricultural decision-making under climate change.

Vegetation Gross Primary Production (GPP) is mainly influenced by the amount of absorbed photosynthetically active radiation (PAR), making absorption by photosynthetic pigments a key determinant of photosynthetic capacity. This study explores the use of the chlorophyll absorption coefficient derived from Sentinel-2 and VENμS satellite data for GPP estimation across three dryland forests in Israel and California between 2017 and 2020. Results indicate high accuracy of GPP estimation using chlorophyll absorption coefficients within the PAR (400–700 nm) and the red-edge (690–740 nm) spectral regions. Sentinel-2-based estimations explained over 91% of GPP variation, while VENμS data accounted for more than 95%. Normalized RMSE values were below 22% for Sentinel-2 and 18% for VENμS without model recalibration across different sites.