Deep-learning framework for optimal selection of soil sampling sites

• Published in: Computers and electronics in agriculture Vol. 217; p. 108650
• Main Authors: Pham, Tan-Hanh, Acharya, Praneel, Bachina, Sravanthi, Osterloh, Kristopher, Nguyen, Kim-Doang
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.02.2024
• Subjects: Binary segmentation; Class imbalanced segmentation; Deep learning; Precision agriculture; Self-attention; Soil sampling; Deep learning; Precision agriculture; Soil sampling; Binary segmentation; Class imbalanced segmentation; Self-attention
• ISSN: 0168-1699; 1872-7107
• DOI: 10.1016/j.compag.2024.108650

Soil sampling is one of the most fundamental agricultural processes. The selection of soil sampling locations within a field plays a crucial role in soil-health analysis. The current soil-sampling techniques produce random samples across a field, which are not representative of the field conditions. This work leverages the recent advancements of deep learning in image processing for finding optimal locations that present the important characteristics of a field. The data for training are collected at different fields in local farms with five features: aspect, flow accumulation, slope, NDVI (normalized difference vegetation index), and yield. The soil sampling dataset is challenging because of the unbalance between the number of pixels that represent soil-sampling spots and the number of pixels that represent the background area. In this work, we approach the problem with two methods, the first approach involves utilizing a state-of-the-art model with the convolutional neural network (CNN) backbone, while the second is to innovate a deep-learning design grounded in the concepts of transformer and self-attention. Our framework is constructed with an encoder–decoder architecture with the self-attention mechanism as the backbone. In the encoder, the self-attention mechanism is the key feature extractor, which produces feature maps. In the decoder, we introduce atrous convolution networks to concatenate, fuse the extracted features, and then export the optimal locations for soil sampling. Currently, the model has achieved impressive results on the testing dataset, with a mean accuracy of 99.52%, a mean Intersection over Union (IoU) of 57.35%, and a mean Dice Coefficient of 71.47%, while the performance metrics of the state-of-the-art CNN-based model are 66.08%, 3.85%, and 1.98%, respectively. This indicates that our proposed model outperforms the CNN-based method on the soil-sampling dataset. To the best of our knowledge, our work is the first to provide a soil-sampling dataset with multiple attributes and leverage deep learning techniques to enable the automatic selection of soil-sampling sites. This work lays a foundation for novel applications of data science and machine-learning technologies to solve other emerging agricultural problems. •The first soil sampling site selection pipeline utilizing deep learning techniques•The tool enables consistently collecting samples at the optimal locations under variable conditions•Developing a deep learning model to adapt multi-input images•Mean accuracy and mIoU on the testing dataset are 99.52% and 57.35%, respectively•A transformer-based segmentation model outperforms the state-of-the-art CNN-based model