基于 BAS-ELM 的无人机高光谱遥感水稻冠层氮含量反演建模

摘要：快速、无损、准确地估算水稻氮含量，有助于及时了解水稻生长状况，对指导稻田管理具有重要意义。为了提高 水稻冠层氮含量高光谱反演精度，以无人机高光谱图像数据和同步测量的水稻冠层氮含量为数据源，采用离散小波多尺 度分解（（ DWMD）对400nm~1000nm范围内的高光谱信息进行降尺度处理，从中提取水稻氮含量反演建模的高光谱特征 变量。并以降维后的变量为数据基础，采用极限学习机（（ ELM）、粒子群优化极限学习机（（ PSO-ELM）、甲虫触角搜索极 限学习机（（BAS-ELM）3种神经网络反演方法，建立水稻氮含量无人机高光谱遥感反演模型，结果表明：（1）利用DWMD 对400~1000nm的高光谱范围进行降维，最终将连续的高光谱反射率信息降维为16个离散的高光谱特征，以便后续进行 水稻氮含量的反演建模。（2）本研究采用的模型中，BAS-ELM的精度最高，其中训练数据的R2、测试数据的R2、训练 数据的RMSE、测试数据的RMSE分别为0.864、0.863、0.247、0.254。

关键词：无人机，氮逆变，水稻，高光谱降维，ELM

期刊：Int J Precis Agric Aviat

DOI：10.33440/j.ijpaa.20200303.105

设备：GaiaSky

BAS-ELM based UAV hyperspectral remote sensing inversion modeling of rice canopy nitrogen content

Abstract：The rapid, nondestructive, and accurate estimation of nitrogen content in rice can help to obtain the growth condition of rice in time, which is of great significance for guiding rice field management. In order to improve the accuracy of high-spectral inversion of rice canopy nitrogen content, the discrete wavelet multiscale decomposition (DWMD) was used to downscale the high- spectral information in the range of 400 nm to 1000 nm by using the UAV hyperspectral image data and the synchronously measured rice canopy nitrogen content as the data source, from which the hyperspectral characteristic variables for rice nitrogen content inversion modeling were extracted. And using the dimensionality reduction variables as the data base, three neural network inversion methods, including extreme learning machines (ELM), particle swarm optimization for extreme learning machines (PSO- ELM), and beetle antennae search algorithm for extreme learning machines (BAS-ELM), were used to establish the rice nitrogen content drone hyperspectral remote sensing inversion model, and the results showed that: (1) The hyperspectral range from 400 nm to 1000 nm was dimensionally reduced by DWMD, and finally the continuous hyperspectral reflectance information was dimensionally reduced to sixteen discrete hyperspectral features for subsequent inversion modelling of rice nitrogen content.(2) In the model adopted in this study, BAS-ELM has the highest accuracy, where the R2 of training data, the R2 of test data, the RMSE of training data, and the RMSE of test data is were 0.864, 0.863, 0.247, 0.254.

Keywords：UAV, Nitrogen inversion, rice, Hyperspectral dimensionality reduction, ELM