College of Natural Resources and Environment, South China Agricultural University, Guangzhou 510642, China.
Guangdong Province Key Laboratory for Land Use and Consolidation, Guangzhou 510642, China.
Sensors (Basel). 2018 Sep 13;18(9):3086. doi: 10.3390/s18093086.
Rapid acquisition of the spatial distribution of soil nutrients holds great implications for farmland soil productivity safety, food security and agricultural management. To this end, we collected 1297 soil samples and measured the content of soil total nitrogen (TN), soil available phosphorus (AP) and soil available potassium (AK) in Zengcheng, north of the Pearl River Delta, China. Hyperspectral remote sensing images (115 bands) of the Chinese Environmental 1A satellite were used as auxiliary variables and dimensionality reduction was performed using Pearson correlation analysis and principal component analysis. The TN, AP and AK of soil were predicted in the study area based on auxiliary variables after dimensionality reduction, along with stepwise linear regression (SLR), support vector machine (SVM), random forest (RF) and back-propagation neural network (BPNN) models; 324 independent points were used to verify the predictive performance. The BPNN model, which demonstrated the best predictive accuracy among all methods, combined ordinary kriging (OK) with mapping the spatial variations of soil nutrients. Results show that the BPNN model with double hidden layers had better predictive accuracy for soil TN (root mean square error () = 0.409 mg kg, ² = 44.24%), soil AP ( = 40.808 mg kg, ² = 42.91%) and soil AK ( = 67.464 mg kg, ² = 48.53%) compared with the SLR, SVM and RF models. The back propagation neural network-ordinary kriging (BPNNOK) model showed the best predictive results of soil TN ( = 0.292 mg kg, ² = 68.51%), soil AP ( = 29.62 mg kg, ² = 69.30%) and soil AK ( = 49.67 mg kg and ² = 70.55%), indicating the best fitting ability between hyperspectral remote sensing bands and soil nutrients. According to the spatial mapping results of the BPNNOK model, concentrations of soil TN (north-central), soil AP (central and southwest) and soil AK (central and southeast) were respectively higher in the study area. The most important bands (464⁻517 nm) for soil TN (b10, b14, b20 and b21), soil AP (b3, b19 and b22) and soil AK (b4, b11, b12 and b25) exhibited the best response and sensitivity according to the SLR, SVM, RF and BPNN models. It was concluded that the application of hyperspectral images (visible-near-infrared data) with BPNNOK model was found to be an efficient method for mapping and monitoring soil nutrients at the regional scale.
快速获取土壤养分的空间分布对农田土壤生产力安全、粮食安全和农业管理具有重要意义。为此，我们在珠江三角洲北部的增城区采集了 1297 个土壤样本，测定了土壤全氮（TN）、土壤有效磷（AP）和土壤速效钾（AK）的含量。利用中国环境 1A 卫星的高光谱遥感图像（115 波段）作为辅助变量，采用 Pearson 相关分析和主成分分析进行降维处理。基于降维后的辅助变量，利用逐步线性回归（SLR）、支持向量机（SVM）、随机森林（RF）和反向传播神经网络（BPNN）模型对研究区的土壤 TN、AP 和 AK 进行预测，并利用 324 个独立点对预测性能进行验证。结果表明，BPNN 模型在所有方法中表现出最好的预测精度，它结合了普通克里金（OK）对土壤养分空间变化的制图。结果表明，与 SLR、SVM 和 RF 模型相比，具有双隐藏层的 BPNN 模型对土壤 TN（均方根误差（）= 0.409 mg kg，² = 44.24%）、土壤 AP（= 40.808 mg kg，² = 42.91%）和土壤 AK（= 67.464 mg kg，² = 48.53%）具有更好的预测精度。反向传播神经网络-普通克里金（BPNNOK）模型对土壤 TN（= 0.292 mg kg，² = 68.51%）、土壤 AP（= 29.62 mg kg，² = 69.30%）和土壤 AK（= 49.67 mg kg，² = 70.55%）的预测结果最好，表明高光谱遥感波段与土壤养分之间具有最好的拟合能力。根据 BPNNOK 模型的空间映射结果，研究区土壤 TN（中北部）、土壤 AP（中部和西南部）和土壤 AK（中部和东南部）的浓度较高。根据 SLR、SVM、RF 和 BPNN 模型，土壤 TN（b10、b14、b20 和 b21）、土壤 AP（b3、b19 和 b22）和土壤 AK（b4、b11、b12 和 b25）最重要的波段（464⁻517nm）表现出最好的响应和灵敏度。总之，利用高光谱图像（可见-近红外数据）和 BPNNOK 模型的应用被发现是一种有效的方法，可用于区域尺度的土壤养分制图和监测。
