# Farmland Extent and Visible Boundary Mapping from 1 m NAIP Imagery Using Residual U-Net and Text-Prompted SAM 3 Refinement

arXiv: https://arxiv.org/abs/2607.21881 · HTML: https://mlsanity.com/paper/2607.21881/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 24 Jul 2026.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Road Extraction by Deep Residual U-Net](https://mlsanity.com/paper/1711.10684/) (2017)
- [Deep learning in agriculture: A survey](https://mlsanity.com/paper/1807.11809/) (2018)
- [The Segment Anything Model (SAM) for Remote Sensing Applications: From Zero to One Shot](https://mlsanity.com/paper/2306.16623/) (2023)
- [Deep learning on edge: extracting field boundaries from satellite images with a convolutional neural network](https://mlsanity.com/paper/1910.12023/) (2019)
- [Fields of The World: A Machine Learning Benchmark Dataset For Global Agricultural Field Boundary Segmentation](https://mlsanity.com/paper/2409.16252/) (2024)
- [Unlocking large-scale crop field delineation in smallholder farming systems with transfer learning and weak supervision](https://mlsanity.com/paper/2201.04771/) (2022)
- [Drone-Based Multispectral Imaging and Deep Learning for Timely Detection of Branched Broomrape in Tomato Farms](https://mlsanity.com/paper/2509.09972/) (2025)
- [Sentinel-2 for Crop Yield Estimation: A Systematic Review](https://mlsanity.com/paper/2603.23779/) (2026)
- [Branched Broomrape Detection in Tomato Farms Using Satellite Imagery and Time-Series Analysis](https://mlsanity.com/paper/2509.10804/) (2025)
- [Investigating the Segment Anything Foundation Model for Mapping Smallholder Agriculture Field Boundaries Without Training Labels](https://mlsanity.com/paper/2407.01846/) (2024)
- [Mapping Tomato Cropping Systems in California Using AlphaEarth Geospatial Embeddings and Deep Learning Analysis](https://mlsanity.com/paper/2605.21804/) (2026)
- [The first global agricultural field boundary map at 10m resolution](https://mlsanity.com/paper/2605.11055/) (2026)
- [Leaf Spectral Reflectance Prediction Using Multi-Head Attention Neural Networks](https://mlsanity.com/paper/2606.01432/) (2026)

## Built on by (most cited first, 4 of 4)

- [From crown candidates to neighborhood screening: integrating optical GeoAI and spatial modeling for urban-canopy assessment in Davis, California](https://mlsanity.com/paper/2608.13856/) (2026)
- [The spatial anatomy of urban wildfire vulnerability: a spatially validated GeoAI framework reveals the roles of building density and vegetation moisture in structure loss during the 2025 Palisades Fire](https://mlsanity.com/paper/2608.22293/) (2026)
- [Multisource Remote Sensing and Geospatial Analysis of Vineyard Wildfire Impacts and Resilience: The 2019 Kincade Fire](https://mlsanity.com/paper/2609.16168/) (2026)
- [A Sentinel-2 benchmark dataset for deep-learning active-fire segmentation across 25 California wildfires](https://mlsanity.com/paper/2609.16199/) (2026)

## Abstract (arXiv)

Agricultural field maps are often proprietary, incomplete, or outdated, yet they provide the spatial framework for crop monitoring, production accounting, and land-conversion analysis. This study presents a reproducible workflow for mapping farmland extent and visible boundaries from 1 m NAIP RGB imagery. Thirty-seven scenes spanning open cropland, peri-urban interfaces, semi-arid irrigation geometries, and fragmented mosaics were annotated in CVAT and converted to binary masks. Non-overlapping 256 x 256 patches yielded 5,698 samples, split by source scene into 3,850 training, 770 validation, and 1,078 test patches. A residual U-Net (ResUNet) trained with a Dice-dominant loss, L = 2.5(1 - Dice) + BCE, achieved test accuracy 0.8808, IoU 0.8605, Dice 0.9234, precision 0.8766, and recall 0.9794. A frozen SAM 3 branch prompted with "agricultural farmland field" was fused with ResUNet by logical OR. On selected difficult patches, Dice improved from 0.858 to 0.955 (orchard rows) and from 0.804 to 0.903 (fragmented parcels). Sliding-window stitching produced coherent regional masks (example tile Dice 0.898 and 0.919). The product is a semantic farmland-extent layer, not a cadastral parcel map, and supports agricultural monitoring where current field layers are unavailable.