Fusion of Reflected GPS Signals With Multispectral Imagery to Estimate Soil Moisture at Subfield Scale From Small UAS Platforms
Fusion of Reflected GPS Signals With Multispectral Imagery to Estimate Soil Moisture at Subfield Scale From Small UAS Platforms
复制标题
融合反射GPS信号与多光谱图像以从小型UAS平台估计子场尺度的土壤湿度
DOI：
10.1109/jstars.2022.3197794
复制
发表时间：
2022
影响因子：
5.5
通讯作者：
V. Senyurek;M. Farhad;A. Gurbuz;M. Kurum;A. Adeli
中科院分区：
文献类型：
--
作者：
V. Senyurek;M. Farhad;A. Gurbuz;M. Kurum;A. Adeli
本研究提出了一种低成本和“概念验证”的方法，通过处理反射全球定位系统（GPS）和小型无人机系统（UAS）平台获得的多光谱相机数据来获得高空间分辨率的土壤水分（SM）。SM估计模型的开发使用随机森林（RF）机器学习（ML）算法，结合从反射GPS信号（收集的智能手机和商业现成的接收器）与辅助植被指数从多光谱相机数据的功能。建议的ML算法使用原位SM测量通过SM探针作为标签。2020年（从1月到11月，包括作物种植到衰老期），在密西西比州立大学（MSU）的装备精良的北方农场对210 × 110米（2.31公顷）的作物田（玉米和棉花）进行了初步田间试验，以获取ML模型训练和测试所需的数据。我们的结果表明，这两个领域可以覆盖GPS反射测量约13分钟的飞行时间在15米的高度，和SM可以映射到5 × 5米的空间分辨率（对应于拉长的第一菲涅尔区）。该模型的训练和验证对8个现场SM站数据集通过十倍和留一探针交叉验证技术。总体而言，十倍交叉验证获得的均方根误差（RMSE）为0.013 m $^{3} m$^{-3}$体积SM和R值为0.95 [-]。在留一探针交叉验证中，该模型的RMSE为0.033 m$^{3}$ m$^{-3}$，R值为0.5 [-]。虽然有有限的数据，结果表明，高分辨率SM测量可以实现与低成本的GPS反射计系统板载一个小型无人机平台，用于精准农业应用。
This study proposes a low-cost and “proof-of-concept” methodology to obtain high spatial resolution soil moisture (SM) via processing reflected global positioning system (GPS) and a multispectral camera data acquired by small unmanned aircraft system (UAS) platforms. An SM estimation model is developed using a random forest (RF) machine-learning (ML) algorithm by combining features obtained from reflected GPS signals (collected by smartphones and commercial off-the-shelf receivers) in conjunction with ancillary vegetation indices from the multispectral camera data. The proposed ML algorithm uses in situ SM measurements acquired via SM probes as labels. A preliminary field experiment was conducted on 210 by 110 m (2.31 ha) crop fields (corn and cotton) in 2020 (from January to November, including crop planting through senescence time period) at Mississippi State University (MSU)’s the heavily instrumented North Farm to acquire data needed for the ML model to train and test. Our results showed that both fields could be covered by GPS reflectometry measurements with about 13 min of flight time at a 15-m altitude, and SM can be mapped with 5 × 5 m spatial resolution (corresponding to the elongated first Fresnel zone). The model is trained with and validated against eight in situ SM station datasets via tenfold and leave-one-probe-out cross-validation techniques. Overall, root-mean-square errors (RMSE) of 0.013 m $^{3}$ m$^{-3}$ volumetric SM and R-value of 0.95 [-] are obtained for tenfold cross validation. The proposed model reached an RMSE of 0.033 m$^{3}$ m$^{-3}$ and an R-value of 0.5 [-] in leave-one-probe-out cross validation. While having limited data, the results indicate that high-resolution SM measurement can be achieved with a low-cost GPS reflectometry system onboard a small UAS platform for use in precision agriculture applications.