Maximum Likelihood (MLH) supervised classification of atmospherically corrected Landsat 8 imagery was applied successfully for delineating main geologic units with a good accuracy (about 90%) according to reliable gro...Maximum Likelihood (MLH) supervised classification of atmospherically corrected Landsat 8 imagery was applied successfully for delineating main geologic units with a good accuracy (about 90%) according to reliable ground truth areas, which reflected the ability of remote sensing data in mapping poorly-accessed and remote regions such as playa (Sabkha) environs, subdued topography and sand dunes. Ground gamma-ray spectrometric survey was to delineate radioactive anomalies within Quaternary sediments at Wadi Diit. The mean absorbed dose rate (D), annual effective dose equivalent (AEDE) and external hazard index (H<sub>ex</sub>) were found to be within the average worldwide ranges. Therefore, Wadi Diit environment is said to be radiological hazard safe except at the black-sand lens whose absorbed dose rate of 100.77 nGy/h exceeds the world average. So, the inhabitants will receive a relatively high radioactive dose generated mainly by monazite and zircon minerals from black-sand lens.展开更多
Cloud detection in remote sensing images is a crucial task in various applications,such as meteorological disaster prediction and earth resource exploration,which require accurate cloud identi¯cation.This work pr...Cloud detection in remote sensing images is a crucial task in various applications,such as meteorological disaster prediction and earth resource exploration,which require accurate cloud identi¯cation.This work proposes a cloud detection model based on the Cloud Detection neural Network(CDNet),incorporating a fusion mechanism of channel and spatial attention.Depthwise separable convolution is adopted to achieve a lightweight network model and enhance the e±ciency of network training and detection.In addition,the Convolutional Block Attention Module(CBAM)is integrated into the network to train the cloud detection model with attention features in channel and spatial dimensions.Experiments were conducted on Landsat 8 imagery to validate the proposed improved CDNet.Averaged over all testing images,the overall accuracy(OA),mean Pixel Accuracy(mPA),Kappa coe±cient and Mean Intersection over Union(MIoU)of improved CDNet were 96.38%,81.18%,96.05%,and 84.69%,respectively.Those results were better than the original CDNet and DeeplabV3+.Experiment results show that the improved CDNet is e®ective and robust for cloud detection in remote sensing images.展开更多
文摘Maximum Likelihood (MLH) supervised classification of atmospherically corrected Landsat 8 imagery was applied successfully for delineating main geologic units with a good accuracy (about 90%) according to reliable ground truth areas, which reflected the ability of remote sensing data in mapping poorly-accessed and remote regions such as playa (Sabkha) environs, subdued topography and sand dunes. Ground gamma-ray spectrometric survey was to delineate radioactive anomalies within Quaternary sediments at Wadi Diit. The mean absorbed dose rate (D), annual effective dose equivalent (AEDE) and external hazard index (H<sub>ex</sub>) were found to be within the average worldwide ranges. Therefore, Wadi Diit environment is said to be radiological hazard safe except at the black-sand lens whose absorbed dose rate of 100.77 nGy/h exceeds the world average. So, the inhabitants will receive a relatively high radioactive dose generated mainly by monazite and zircon minerals from black-sand lens.
基金supported by the National Natural Science Foundation of China (61973164,62373192).
文摘Cloud detection in remote sensing images is a crucial task in various applications,such as meteorological disaster prediction and earth resource exploration,which require accurate cloud identi¯cation.This work proposes a cloud detection model based on the Cloud Detection neural Network(CDNet),incorporating a fusion mechanism of channel and spatial attention.Depthwise separable convolution is adopted to achieve a lightweight network model and enhance the e±ciency of network training and detection.In addition,the Convolutional Block Attention Module(CBAM)is integrated into the network to train the cloud detection model with attention features in channel and spatial dimensions.Experiments were conducted on Landsat 8 imagery to validate the proposed improved CDNet.Averaged over all testing images,the overall accuracy(OA),mean Pixel Accuracy(mPA),Kappa coe±cient and Mean Intersection over Union(MIoU)of improved CDNet were 96.38%,81.18%,96.05%,and 84.69%,respectively.Those results were better than the original CDNet and DeeplabV3+.Experiment results show that the improved CDNet is e®ective and robust for cloud detection in remote sensing images.
