Soil Sampling Map Optimization with a Dual Deep Learning Framework

被引:2
|
作者
Pham, Tan-Hanh [1 ]
Nguyen, Kim-Doang [1 ]
机构
[1] Florida Inst Technol, Dept Mech & Civil Engn, Melbourne, FL 32901 USA
来源
基金
美国食品与农业研究所;
关键词
soil sampling; precision agriculture; multi-spectral imaging; deep learning; highly unbalanced segmentation;
D O I
10.3390/make6020035
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Soil sampling constitutes a fundamental process in agriculture, enabling precise soil analysis and optimal fertilization. The automated selection of accurate soil sampling locations representative of a given field is critical for informed soil treatment decisions. This study leverages recent advancements in deep learning to develop efficient tools for generating soil sampling maps. We proposed two models, namely UDL and UFN, which are the results of innovations in machine learning architecture design and integration. The models are meticulously trained on a comprehensive soil sampling dataset collected from local farms in South Dakota. The data include five key attributes: aspect, flow accumulation, slope, normalized difference vegetation index, and yield. The inputs to the models consist of multispectral images, and the ground truths are highly unbalanced binary images. To address this challenge, we innovate a feature extraction technique to find patterns and characteristics from the data before using these refined features for further processing and generating soil sampling maps. Our approach is centered around building a refiner that extracts fine features and a selector that utilizes these features to produce prediction maps containing the selected optimal soil sampling locations. Our experimental results demonstrate the superiority of our tools compared to existing methods. During testing, our proposed models exhibit outstanding performance, achieving the highest mean Intersection over Union of 60.82% and mean Dice Coefficient of 73.74%. The research not only introduces an innovative tool for soil sampling but also lays the foundation for the integration of traditional and modern soil sampling methods. This work provides a promising solution for precision agriculture and soil management.
引用
收藏
页码:751 / 769
页数:19
相关论文
共 50 条
  • [1] Deep-learning framework for optimal selection of soil sampling sites
    Pham, Tan-Hanh
    Acharya, Praneel
    Bachina, Sravanthi
    Osterloh, Kristopher
    Nguyen, Kim-Doang
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2024, 217
  • [2] Deep-learning framework for optimal selection of soil sampling sites
    Pham, Tan-Hanh
    Acharya, Praneel
    Bachina, Sravanthi
    Osterloh, Kristopher
    Nguyen, Kim-Doang
    Computers and Electronics in Agriculture, 2024, 217
  • [3] Intelligent Map Reader: A Framework for Topographic Map Understanding With Deep Learning and Gazetteer
    Li, Huali
    Liu, Jun
    Zhou, Xiran
    IEEE ACCESS, 2018, 6 : 25363 - 25376
  • [4] A batched GEMM optimization framework for deep learning
    Yang, Zhiwei
    Lu, Lu
    Wang, Ruimin
    JOURNAL OF SUPERCOMPUTING, 2022, 78 (11): : 13393 - 13408
  • [5] A batched GEMM optimization framework for deep learning
    Zhiwei Yang
    Lu Lu
    Ruimin Wang
    The Journal of Supercomputing, 2022, 78 : 13393 - 13408
  • [6] RadioCycle: Deep Dual Learning based Radio Map Estimation
    Zheng, Yi
    Zhang, Tianqian
    Liao, Cunyi
    Wang, Ji
    Liu, Shouyin
    KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS, 2022, 16 (11): : 3780 - 3797
  • [7] An Integrated Deep Learning Framework for Soil Type Classification
    Shruti Jalapur
    Nagamma Patil
    SN Computer Science, 6 (3)
  • [8] Dual sampling neural network: Learning without explicit optimization
    Teramae, Jun-nosuke
    Tsubo, Yasuhiro
    PHYSICAL REVIEW RESEARCH, 2022, 4 (04):
  • [9] Sampling scheme optimization to map soil depth to petrocalcic horizon at field scale
    Beatriz Domenech, Marisa
    Castro-Franco, Mauricio
    Luis Costa, Jose
    Mabel Amiotti, Nilda
    GEODERMA, 2017, 290 : 75 - 82
  • [10] Statistical Learning in Soil Sampling Design Aided by Pareto Optimization
    Israeli, Assaf
    Emmerich, Michael
    Litaor, Michael
    Shir, Ofer M.
    PROCEEDINGS OF THE 2019 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO'19), 2019, : 1198 - 1205