scholarly journals Deep Learning Convolutional Neural Network for the Retrieval of Land Surface Temperature from AMSR2 Data in China

Sensors ◽  
2019 ◽  
Vol 19 (13) ◽  
pp. 2987 ◽  
Author(s):  
Jiancan Tan ◽  
Nusseiba NourEldeen ◽  
Kebiao Mao ◽  
Jiancheng Shi ◽  
Zhaoliang Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Surface Temperature ◽  
Convolutional Neural Network ◽  
Land Surface Temperature ◽  
Land Surface ◽  
Measurement Data ◽  
Retrieval Algorithm ◽  
Observation Data ◽  
Moderate Resolution Imaging Spectroradiometer ◽  
Better Than

A convolutional neural network (CNN) algorithm was developed to retrieve the land surface temperature (LST) from Advanced Microwave Scanning Radiometer 2 (AMSR2) data in China. Reference data were selected using the Moderate Resolution Imaging Spectroradiometer (MODIS) LST product to overcome the problem related to the need for synchronous ground observation data. The AMSR2 brightness temperature (TB) data and MODIS surface temperature data were randomly divided into training and test datasets, and a CNN was constructed to simulate passive microwave radiation transmission to invert the surface temperature. The twelve V/H channel combinations (7.3, 10.65, 18.7, 23.8, 36.5, 89 GHz) resulted in the most stable and accurate CNN retrieval model. Vertical polarizations performed better than horizontal polarizations; however, because CNNs rely heavily on large amounts of data, the combination of vertical and horizontal polarizations performed better than a single polarization. The retrievals in different regions indicated that the CNN accuracy was highest over large bare land areas. A comparison of the retrieval results with ground measurement data from meteorological stations yielded R2 = 0.987, RMSE = 2.69 K, and an average relative error of 2.57 K, which indicated that the accuracy of the CNN LST retrieval algorithm was high and the retrieval results can be applied to long-term LST sequence analysis in China.

Estimating Land Surface Temperature from AMSR-E and AMSR2 Data with Convolutional Neural Network

2021 ◽  
Author(s):  
Shaofei Wang ◽  
Ji Zhou ◽  
Xiaodong Zhang ◽  
Zichun Jin
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Neural Networks ◽  
Surface Temperature ◽  
Convolutional Neural Network ◽  
Root Mean Square ◽  
Air Temperature ◽  
Land Surface Temperature ◽  
Land Surface ◽  
Mean Square

<p>Land surface temperature (LST) is a key factor in earth–atmosphere interactions and an important indicator for monitoring environmental changes and energy balance on Earth's surface. Thermal infrared (TIR) remote sensing can only obtain valid observations under clear-sky conditions, which results in the discontinuities of the LST time series. In contrast, passive microwave (PMW) remote sensing can help estimate the LST under cloudy conditions and the LST generated by PMW observations is an important input parameter for generating medium-resolution (e.g., 1km) all-weather LST. Neural networks, especially the latest deep learning, have exhibited good ability in estimating surface parameters from satellite remote sensing. However, thorough examinations of neural networks in the estimation of LST from satellite PMW observations are still lacking. In this study, we examined the performances of the traditional neural network (NN), deep belief network (DBN), and convolutional neural network (CNN) in estimating LST from the Advanced Microwave Scanning Radiometer for EOS (AMSR-E) and Advanced Microwave Scanning Radiometer 2 (AMSR2) data over the Chinese landmass. The examination results show that CNN is better than NN and DBN by 0.1–0.4 K. Different combinations of input parameters were examined to get the best combinations for the daytime and nighttime conditions. The best combinations are the brightness temperatures (BTs), NDVI, air temperature, and day of the year (DOY) for the daytime and BTs and air temperature for the nighttime. Compared with the MODIS LST, the CNN LST estimates yielded root-mean-square differences (RMSDs) of 2.19–3.58 K for the daytime and 1.43–2.14 K for the nighttime for diverse land cover types for AMSR-E. Validation based on the in-situ LST demonstrates that the CNN LST yielded root-mean-square errors of 2.10–5.34 K and the error analysis confirms that the main reason for the errors is the scale mismatching between the ground stations and the MW pixels. This study helps better the understanding of the use of neural networks for estimating LST from satellite MW observations.</p>

scholarly journals Reconstructing Geostationary Satellite Land Surface Temperature Imagery Based on a Multiscale Feature Connected Convolutional Neural Network

2019 ◽  
Vol 11 (3) ◽  
pp. 300 ◽  
Author(s):  
Penghai Wu ◽  
Zhixiang Yin ◽  
Hui Yang ◽  
Yanlan Wu ◽  
Xiaoshuang Ma
Keyword(s):  
Neural Network ◽  
Missing Data ◽  
Surface Temperature ◽  
Convolutional Neural Network ◽  
Land Surface Temperature ◽  
Land Surface ◽  
Missing Values ◽  
Geostationary Satellite ◽  
Reconstruction Methods ◽  
Highly Nonlinear

Geostationary satellite land surface temperature (GLST) data are important for various dynamic environmental and natural resource applications for terrestrial ecosystems. Due to clouds, shadows, and other atmospheric conditions, the derived LSTs are often missing a large number of values. Reconstructing the missing values is essential for improving the usability of the geostationary satellite LST data. However, current reconstruction methods mainly aim to fill the values of a small number of invalid pixels with many valid pixels, which can provide useful land surface temperature values. When the missing data extent becomes large, the reconstruction effect will worsen because the relationship between different spatiotemporal geostationary satellite LSTs is complex and highly nonlinear. Inspired by the superiority of the deep convolutional neural network (CNN) in solving highly nonlinear and dynamic problems, a multiscale feature connection CNN model is proposed to fill missing LSTs with large missing regions. The proposed method has been tested on both FengYun-2G and Meteosat Second Generation-Spinning Enhanced Visible and InfraRed Imager geostationary satellite LST datasets. The results of simulated and actual experiments show that the proposed method is accurate to within about 1 °C, with 70% missing data rates. This is feasible and effective for large regions of LST reconstruction tasks.

scholarly journals Estimating Land Surface Temperature from Satellite Passive Microwave Observations with the Traditional Neural Network, Deep Belief Network, and Convolutional Neural Network

2020 ◽  
Vol 12 (17) ◽  
pp. 2691 ◽  
Author(s):  
Shaofei Wang ◽  
Ji Zhou ◽  
Tianjie Lei ◽  
Hua Wu ◽  
Xiaodong Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Surface Temperature ◽  
Convolutional Neural Network ◽  
Spatial Resolution ◽  
Air Temperature ◽  
Land Surface Temperature ◽  
Land Surface ◽  
Passive Microwave ◽  
Mean Square

Neural networks, especially the latest deep learning, have exhibited good ability in estimating surface parameters from satellite remote sensing. However, thorough examinations of neural networks in the estimation of land surface temperature (LST) from satellite passive microwave (MW) observations are still lacking. Here, we examined the performances of the traditional neural network (NN), deep belief network (DBN), and convolutional neural network (CNN) in estimating LST from the AMSR-E and AMSR2 data over the Chinese landmass. The examinations were based on the same training set, validation set, and test set extracted from 2003, 2004, and 2009, respectively, for AMSR-E with a spatial resolution of 0.25°. For AMSR2, the three sets were extracted from 2013, 2014, and 2016 with a spatial resolution of 0.1°, respectively. MODIS LST played the role of “ground truth” in the training, validation, and testing. The examination results show that CNN is better than NN and DBN by 0.1–0.4 K. Different combinations of input parameters were examined to get the best combinations for the daytime and nighttime conditions. The best combinations are the brightness temperatures (BTs), NDVI, air temperature, and day of the year (DOY) for the daytime and BTs and air temperature for the nighttime. By adding three and one easily obtained parameters on the basis of BTs, the accuracies of LST estimates can be improved by 0.8 K and 0.3 K for the daytime and nighttime conditions, respectively. Compared with the MODIS LST, the CNN LST estimates yielded root-mean-square differences (RMSDs) of 2.19–3.58 K for the daytime and 1.43–2.14 K for the nighttime for diverse land cover types for AMSR-E. Validation against the in-situ LSTs showed that the CNN LSTs yielded root-mean-square errors of 2.10–4.72 K for forest and cropland sites. Further intercomparison indicated that ~50% of the CNN LSTs were closer to the MODIS LSTs than ESA’s GlobTemperature AMSR-E LSTs, and the average RMSDs of the CNN LSTs were less than 3 K over dense vegetation compared to NASA’s global land parameter data record air temperatures. This study helps better the understanding of the use of neural networks for estimating LST from satellite MW observations.

scholarly journals Analysis of the Spatiotemporal Change in Land Surface Temperature for a Long-Term Sequence in Africa (2003–2017)

2020 ◽  
Vol 12 (3) ◽  
pp. 488 ◽  
Author(s):  
Nusseiba NourEldeen ◽  
Kebiao Mao ◽  
Zijin Yuan ◽  
Xinyi Shen ◽  
Tongren Xu ◽  
...  
Keyword(s):  
Surface Temperature ◽  
Land Surface Temperature ◽  
Land Surface ◽  
Observation Data ◽  
The West ◽  
Thermal Infrared Remote Sensing ◽  
Ground Station ◽  
Station Data ◽  
Effects Of Temperature ◽  
Reconstruction Model

It is very important to understand the temporal and spatial variations of land surface temperature (LST) in Africa to determine the effects of temperature on agricultural production. Although thermal infrared remote sensing technology can quickly obtain surface temperature information, it is greatly affected by clouds and rainfall. To obtain a complete and continuous dataset on the spatiotemporal variations in LST in Africa, a reconstruction model based on the moderate resolution imaging spectroradiometer (MODIS) LST time series and ground station data was built to refactor the LST dataset (2003–2017). The first step in the reconstruction model is to filter low-quality LST pixels contaminated by clouds and then fill the pixels using observation data from ground weather stations. Then, the missing pixels are interpolated using the inverse distance weighting (IDW) method. The evaluation shows that the accuracy between reconstructed LST and ground station data is high (root mean square er–ror (RMSE) = 0.84 °C, mean absolute error (MAE) = 0.75 °C and correlation coefficient (R) = 0.91). The spatiotemporal analysis of the LST indicates that the change in the annual average LST from 2003–2017 was weak and the warming trend in Africa was remarkably uneven. Geographically, “the warming is more pronounced in the north and the west than in the south and the east”. The most significant warming occurred near the equatorial region in South Africa (slope > 0.05, R > 0.61, p < 0.05) and the central (slope = 0.08, R = 0.89, p < 0.05) regions, and a nonsignificant decreasing trend occurred in Botswana. Additionally, the mid-north region (north of Chad, north of Niger and south of Algeria) became colder (slope > −0.07, R = 0.9, p < 0.05), with a nonsignificant trend. Seasonally, significant warming was more pronounced in winter, mostly in the west, especially in Mauritania (slope > 0.09, R > 0.9, p < 0.5). The response of the different types of surface to the surface temperature has shown variability at different times, which provides important information to understand the effects of temperature changes on crop yields, which is critical for the planning of agricultural farming systems in Africa.

Sign in / Sign up

Export Citation Format

Share Document