Hsieh, T.-H.T.-H.HsiehJEAN-FU KIANG2021-05-052021-05-052020https://www.scopus.com/inward/record.url?eid=2-s2.0-85082397744&partnerID=40&md5=4934af039f2b484bc575c981134e425bhttps://scholars.lib.ntu.edu.tw/handle/123456789/559016Several versions of convolutional neural network (CNN) were developed to classify hyperspectral images (HSIs) of agricultural lands, including 1D-CNN with pixelwise spectral data, 1D-CNN with selected bands, 1D-CNN with spectral-spatial features and 2D-CNN with principal components. The HSI data of a crop agriculture in Salinas Valley and a mixed vegetation agriculture in Indian Pines were used to compare the performance of these CNN algorithms. The highest overall accuracy on these two cases are 99.8% and 98.1%, respectively, achieved by applying 1D-CNN with augmented input vectors, which contain both spectral and spatial features embedded in the HSI data. © 2020 by the authors. Licensee MDPI, Basel, Switzerland.Agriculture; Convolutional neural network (CNN); Hyperspectral image (HSI); Principal component analysis (PCA)[SDGs]SDG2[SDGs]SDG13[SDGs]SDG15Agriculture; Convolution; Convolutional neural networks; Principal component analysis; Spectroscopy; Agricultural land; Input vector; Overall accuracies; Principal Components; Spatial features; Spectral data; Image classification; agricultural land; article; case report; clinical article; convolutional neural network; principal component analysis; vegetationjournal article10.3390/s20061734322449292-s2.0-85082397744WOS:000529139700192