Alina Zare – Machine Learning and Sensing Lab

PublicationPublication

Assessing Transferability of Remote Sensing Pasture Estimates Using Multiple Machine Learning Algorithms and Evaluation Structures

October 25, 2025 in Journal Papers, Publication

Abstract: Both the vastness of pasturelands and the value they contain—e.g., food security, ecosystem services—have resulted in increased scientific and industry efforts to remotely monitor them via satellite imagery and machine learning (ML). However, the transferability of these models is… Read More

agricultural monitoring ecological modeling generalization challenges gradient boosting model transferability multispectral data nitrogen concentration estimation pasture biomass estimation pasturelands Precision Agriculture remote sensing satellite imagery Sentinel-2 spatial heterogeneity spatiotemporal dependence temporal heterogeneity

Plant parasitic nematode identification in complex samples with deep learning

October 24, 2025 in Journal Papers, Publication

Abstract: Plant parasitic nematodes are significant contributors to yield loss worldwide, causing devastating losses to every crop species, in every climate. Mitigating these losses requires swift and informed management strategies, centered on identification and quantification of field populations. Current plant… Read More

agricultural bioinformatics agriculture pests automated detection crop yield loss dataset annotation deep learning object detection high-throughput phenotyping manual analysis challenges microscopy images nematode identification nematology plant disease management plant parasitic nematodes Precision Agriculture soil extractions

Histogram Layers for Neural “Engineered” Features

July 23, 2025 in Journal Papers, Publication

Abstract: In the computer vision literature, many effective histogram-based features have been developed. These engineered features include local binary patterns and edge histogram descriptors among others and they have been shown to be informative features for a variety of computer… Read More

#Image Classification benchmark datasets computer vision convolutional neural networks deep learning edge histogram descriptors feature learning Histogram features learned descriptors local binary patterns neural networks real-world datasets

Facilitating macrosystem biology with organismal-scale airborne remote sensing: Challenges and opportunities

July 14, 2025 in Journal Papers, Publication

Abstract: Emergent ecosystem properties, such as population and trait distributions, biodiversity and energy and water fluxes, occur because of the dynamic interactions of individuals in their environment. Remote sensing, where image data is collected over large areas, can provide information… Read More

Biodiversity Bird Detection Cross-Ecosystem Generalization Data Processing Pipelines deep learning Ecological Data Products Ecological Knowledge Integration Emergent Ecosystem Properties Energy Fluxes Individual Detection Interdisciplinary Collaboration Limited Field Data Macrosystem Biology Mammal Monitoring Object Delineation Organism Characterization Organismal Remote Sensing Population Distributions remote sensing Sensor Transferability Trait Distributions Tree Mapping Uncertainty Quantification Water Fluxes

Toward a General Framework for AI‑Enabled Prediction in Crop Improvement

July 14, 2025 in Journal Papers, Publication

Abstract: The curse of dimensionality in genomic prediction has been established and hampers genetic gain for complex traits. Artificial intelligence (AI) that fuses symbolic and sub-symbolic approaches to prediction is emerging as an approach that can deal effectively with this… Read More

Artificial Intelligence (AI) Bayesian Statistics Breeding Systems Complex Traits Crop Improvement Curse of Dimensionality Data-Driven Decision Making Dynamical Systems Ensemble Models Genetic Gain Genetic Networks Genomic Prediction Heritability Knowledge Integration Physiological Networks Predictability Limits Predictive Modeling Symbolic and Sub-symbolic AI Systems Biology

Multi-Task Learning with Multi-Annotation Triplet Loss for Improved Object Detection

April 10, 2025 in Conference Papers, Publication

Abstract: Triplet loss traditionally relies only on class labels and does not use all available information in multi-task scenarios where multiple types of annotations are available. This paper introduces a Multi-Annotation Triplet Loss (MATL) framework that extends triplet loss by… Read More

aerial imagery bounding box annotations classification computer vision deep learning localization metric learning multi-annotation learning multi-task learning representation learning triplet loss wildlife monitoring

Interactive Segmentation with Prototype Learning for Few-Shot Root Annotation

April 10, 2025 in Journal Papers, Publication

Abstract: Fine-scale pixel-level annotation of minirhizotron root images is a less common and challenging task. We present an interactive segmentation framework to accelerate root annotation. We leverage the concept of few-shot segmentation so that the pre-trained model can be effectively… Read More

Adaptation models Annotations Computational modeling Data models feature extraction few-shot Image segmentation Prototypes Real-time systems transfer learning

Automated potato tuber mass estimation and grading with multiangle 2D images

February 13, 2025 in Journal Papers, Publication

Abstract: Estimating potato tuber mass and size grading with computer vision can help breeders, farmers, and potato processing units reduce manual labor for potato post-harvest handling through optimized technology. The objective of the study was to estimate potato tuber mass… Read More

2D Imaging Agricultural Technology computer vision Crop Phenotyping Geometric Feature Analysis Image-Based Feature Extraction Multiview Imaging Post-Harvest Automation Potato Tuber Mass Estimation Precision Agriculture Random Forest Classification Regression Models Size Grading

Quantifying Heterogeneous Ecosystem Services with Multi-Label Soft Classification

October 17, 2024 in Conference Papers, Publication

Abstract: Understanding and quantifying ecosystem services are crucial for sustainable environmental management, conservation efforts, and policy-making. The advancement of remote sensing technology and machine learning techniques has greatly facilitated this process. Yet, ground truth labels, such as biodiversity, are very… Read More

Individual canopy tree species maps for the National Ecological Observatory Network

October 17, 2024 in Journal Papers, Publication

Abstract: The ecology of forest ecosystems depends on the composition of trees. Capturing fine-grained information on individual trees at broad scales provides a unique perspective on forest ecosystems, forest restoration and responses to disturbance. Individual tree data at wide extents… Read More