# Crop identification using deep learning on LUCAS crop cover photos

arXiv: https://arxiv.org/abs/2305.04994 · HTML: https://mlsanity.com/paper/2305.04994/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 45 references that are in the map.
- First posted on arXiv 8 May 2023.

## Builds on (most cited first, 8 of 8)

- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Using Deep Learning for Image-Based Plant Disease Detection](https://mlsanity.com/paper/1604.03169/) (2016)
- [Macro F1 and Macro F1](https://mlsanity.com/paper/1911.03347/) (2019)
- [Deep Learning and Machine Vision for Food Processing: A Survey](https://mlsanity.com/paper/2103.16106/) (2021)
- [Monitoring crop phenology with street-level imagery using computer vision](https://mlsanity.com/paper/2112.09190/) (2021)
- [AI-enabled Efficient and Safe Food Supply Chain](https://mlsanity.com/paper/2105.00333/) (2021)

## Built on by (most cited first, 5 of 5)

- [AgroBench: Vision-Language Model Benchmark in Agriculture](https://mlsanity.com/paper/2507.20519/) (2025)
- [AgriBench: A Hierarchical Agriculture Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2412.00465/) (2024)
- [A survey of datasets for computer vision in agriculture](https://mlsanity.com/paper/2502.16950/) (2025)
- [Benchmarking Vision-Language Models for Microscopic Plant Image Understanding](https://mlsanity.com/paper/2606.22497/) (2026)
- [AgriField-40K: Adapting Vision Models to Agriculture With Efficient Continual Pretraining](https://mlsanity.com/paper/2608.07984/) (2026)

## Abstract (arXiv)

Crop classification via deep learning on ground imagery can deliver timely and accurate crop-specific information to various stakeholders. Dedicated ground-based image acquisition exercises can help to collect data in data scarce regions, improve control on timing of collection, or when study areas are to small to monitor via satellite. Automatic labelling is essential when collecting large volumes of data. One such data collection is the EU's Land Use Cover Area frame Survey (LUCAS), and in particular, the recently published LUCAS Cover photos database. The aim of this paper is to select and publish a subset of LUCAS Cover photos for 12 mature major crops across the EU, to deploy, benchmark, and identify the best configuration of Mobile-net for the classification task, to showcase the possibility of using entropy-based metrics for post-processing of results, and finally to show the applications and limitations of the model in a practical and policy relevant context. In particular, the usefulness of automatically identifying crops on geo-tagged photos is illustrated in the context of the EU's Common Agricultural Policy. The work has produced a dataset of 169,460 images of mature crops for the 12 classes, out of which 15,876 were manually selected as representing a clean sample without any foreign objects or unfavorable conditions. The best performing model achieved a Macro F1 (M-F1) of 0.75 on an imbalanced test dataset of 8,642 photos. Using metrics from information theory, namely - the Equivalence Reference Probability, resulted in achieving an increase of 6%. The most unfavorable conditions for taking such images, across all crop classes, were found to be too early or late in the season. The proposed methodology shows the possibility for using minimal auxiliary data, outside the images themselves, in order to achieve a M-F1 of 0.817 for labelling between 12 major European crops.