Deep neural network regression for estimating land surface temperature at 10 meter spatial resolution using Landsat-8 and Sentinel-2 data

The frequency of extreme heat related events is rising. This places the ever growing number of urban dwellers at higher risk. Quantifying these phenomena is important for the development and monitoring of climate change adaptation and mitigation policies. In this context, earth observations offer increasing opportunities to assess these phenomena with an unprecedented level of accuracy and spatial reach. Satellite thermal imaging systems acquire Land Surface Temperature (LST) which is fundamental to run models that study for example hotspots and heatwaves in urban environments.Current instruments include TIRS on board Landsat 8 and MODIS on board of Terra satellites. These provide LST products on a monthly basis at 100m and twice per day at 1km respectively. Other sensors on board geostationary satellites, such as MSG and GOES-R, produce sub-hourly thermal images. For example the SEVIRI instrument onboard MSG, captures images every 15 minutes. However, this is done at an even coarser spatial resolution, which is 3 to 5 km in the case of SEVIRI. Nevertheless, none of the existing systems can capture LST synchronously with fine spatial resolution at a high temporal frequency, which is a prerequisite for monitoring heat stress in urban environments.Combining LST time series of high temporal resolution (i.e. sub-daily MODIS- or SEVIRI-derived data) with products of fine spatial resolution (i.e. Landsat 8 products), and potentially other related variables (i.e. reflectance, spectral indices, land cover information, terrain parameters and local climatic variables), facilitates the downscaling of LST estimations. Nonetheless, considering the complexity of how distinct surfaces within a city heat-up differently during the course of a day, such a downscaling is meaningful for practically synchronous observations (e.g. Landsat-8 and MODIS Terra&#8217;s morning observations).The recently launched ECOSTRESS mission provides multiple times in a day high spatial resolution thermal imagery at 70m. Albeit, recording the same locations on Earth every few days at varying times. We explore the associations between ECOSTRESS and Landsat-8 thermal data, based on the incoming radiation load and distinct surface properties characterised from other datasets. In our approach, first we upscale ECOSTRESS data to simulate Landsat-8 images at moments that coincide the acquisition times of other sensors products. In a second step, using the simulated Landsat-8 images, we downscale LST products acquired at later times, such as MODIS Aqua (ca. 13:30) or even the hourly MSG data. This composite downscaling procedure enables an enhanced LST estimation that opens the way for better diagnostics of the heat stress in urban landscapes.In this study we discuss in detail the concepts of our approach and present preliminary results produced with the JEODPP, JRC's high throughput computing platform.

Download Full-text

Downscaling MODIS land surface temperature to Sentinel-2 spatial resolution in the Barrax test site

Seventh International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2019) ◽

10.1117/12.2533442 ◽

2019 ◽

Author(s):

Juan Manuel Sánchez ◽

Joan Miquel Galve ◽

José González-Piqueras ◽

Ramón López-Urrea ◽

Raquel Niclòs ◽

...

Keyword(s):

Surface Temperature ◽

Spatial Resolution ◽

Land Surface Temperature ◽

Land Surface ◽

Test Site ◽

Modis Land Surface Temperature ◽

Sentinel 2

Download Full-text

FUSION OF LANDSAT- 8 THERMAL INFRARED AND VISIBLE BANDS WITH MULTI-RESOLUTION ANALYSIS CONTOURLET METHODS

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-4-w4-77-2017 ◽

2017 ◽

Vol XLII-4/W4 ◽

pp. 77-81 ◽

Cited By ~ 1

Author(s):

F. Farhanj ◽

M. Akhoondzadeh

Keyword(s):

Surface Temperature ◽

Image Fusion ◽

Spatial Resolution ◽

Land Surface Temperature ◽

Land Surface ◽

Spatial Information ◽

Thermal Infrared ◽

Landsat 8 ◽

Multi Resolution Analysis ◽

Resolution Analysis

Land surface temperature image is an important product in many lithosphere and atmosphere applications. This image is retrieved from the thermal infrared bands. These bands have lower spatial resolution than the visible and near infrared data. Therefore, the details of temperature variation can't be clearly identified in land surface temperature images. The aim of this study is to enhance spatial information in thermal infrared bands. Image fusion is one of the efficient methods that are employed to enhance spatial resolution of the thermal bands by fusing these data with high spatial resolution visible bands. Multi-resolution analysis is an effective pixel level image fusion approach. In this paper, we use contourlet, non-subsampled contourlet and sharp frequency localization contourlet transform in fusion due to their advantages, high directionality and anisotropy. The absolute average difference and RMSE values show that with small distortion in the thermal content, the spatial information of the thermal infrared and the land surface temperature images is enhanced.

Download Full-text

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

Remote Sensing ◽

10.3390/rs12172691 ◽

2020 ◽

Vol 12 (17) ◽

pp. 2691 ◽

Cited By ~ 1

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.

Download Full-text

Exploratory Analysis of Urban Climate Using a Gap-Filled Landsat 8 Land Surface Temperature Data Set

Sensors ◽

10.3390/s20185336 ◽

2020 ◽

Vol 20 (18) ◽

pp. 5336

Author(s):

Sorin Cheval ◽

Alexandru Dumitrescu ◽

Vlad-Alexandru Amihaesei

Keyword(s):

Surface Temperature ◽

Urban Area ◽

Spatial Resolution ◽

Land Surface Temperature ◽

Land Surface ◽

Urban Climate ◽

Temperature Data ◽

Landsat 8 ◽

Data Set ◽

Surface Temperature Data

The Landsat 8 satellites have retrieved land surface temperature (LST) resampled at a 30-m spatial resolution since 2013, but the urban climate studies frequently use a limited number of images due to the problems related to missing data over the city of interest. This paper endorses a procedure for building a long-term gap-free LST data set in an urban area using the high-resolution Landsat 8 imagery. The study is applied on 94 images available through 2013–2018 over Bucharest (Romania). The raw images containing between 1.1% and 58.4% missing LST data were filled in using the Data INterpolating Empirical Orthogonal Functions (DINEOF) algorithm implemented in the sinkr R packages. The resulting high-spatial-resolution gap-filled land surface temperature data set was used to explore the LST climatology over Bucharest (Romania) an urban area, at a monthly, seasonal, and annual scale. The performance of the gap-filling method was checked using a cross-validation procedure, and the results pledge for the development of an LST-based urban climatology.

Download Full-text

Optimized AVHRR land surface temperature downscaling method for local scale observations: case study for the coastal area of the Gulf of Gdańsk

Open Geosciences ◽

10.1515/geo-2017-0032 ◽

2017 ◽

Vol 9 (1) ◽

Cited By ~ 1

Author(s):

Andrzej Chybicki ◽

Zbigniew Łubniewski

Keyword(s):

Surface Temperature ◽

Spatial Resolution ◽

Land Surface Temperature ◽

Land Surface ◽

Local Scale ◽

Reference Image ◽

Landsat 8 ◽

Gulf Of Gdańsk ◽

Downscaling Method ◽

Gulf Of Gdansk

AbstractSatellite imaging systems have known limitations regarding their spatial and temporal resolution. The approaches based on subpixel mapping of the Earth’s environment, which rely on combining the data retrieved from sensors of higher temporal and lower spatial resolution with the data characterized by lower temporal but higher spatial resolution, are of considerable interest. The paper presents the downscaling process of the land surface temperature (LST) derived from low resolution imagery acquired by the Advanced Very High Resolution Radiometer (AVHRR), using the inverse technique. The effective emissivity derived from another data source is used as a quantity describing thermal properties of the terrain in higher resolution, and allows the downsampling of low spatial resolution LST images. The authors propose an optimized downscaling method formulated as the inverse problem and show that the proposed approach yields better results than the use of other downsampling methods. The proposed method aims to find estimation of high spatial resolution LST data by minimizing the global error of the downscaling. In particular, for the investigated region of the Gulf of Gdansk, the RMSE between the AVHRR image downscaled by the proposed method and the Landsat 8 LST reference image was 2.255°C with correlation coefficient R equal to 0.828 and Bias = 0.557°C. For comparison, using the PBIM method, it was obtained RMSE = 2.832°C, R = 0.775 and Bias = 0.997°C for the same satellite scene. It also has been shown that the obtained results are also good in local scale and can be used for areas much smaller than the entire satellite imagery scene, depicting diverse biophysical conditions. Specifically, for the analyzed set of small sub-datasets of the whole scene, the obtained RSME between the downscaled and reference image was smaller, by approx. 0.53°C on average, in the case of applying the proposed method than in the case of using the PBIM method.

Download Full-text

A Data Fusion Modeling Framework for Retrieval of Land Surface Temperature from Landsat-8 and MODIS Data

Sensors ◽

10.3390/s20154337 ◽

2020 ◽

Vol 20 (15) ◽

pp. 4337

Author(s):

Guohui Zhao ◽

Yaonan Zhang ◽

Junlei Tan ◽

Cong Li ◽

Yanrun Ren

Keyword(s):

Data Fusion ◽

Environmental Change ◽

Surface Temperature ◽

Spatial Resolution ◽

Temporal Resolution ◽

Land Surface Temperature ◽

Land Surface ◽

Landsat 8 ◽

Modeling Framework ◽

The Mean

Land surface temperature (LST) is a critical state variable of land surface energy equilibrium and a key indicator of environmental change such as climate change, urban heat island, and freezing-thawing hazard. The high spatial and temporal resolution datasets are urgently needed for a variety of environmental change studies, especially in remote areas with few LST observation stations. MODIS and Landsat satellites have complementary characteristics in terms of spatial and temporal resolution for LST retrieval. To make full use of their respective advantages, this paper developed a pixel-based multi-spatial resolution adaptive fusion modeling framework (called pMSRAFM). As an instance of this framework, the data fusion model for joint retrieval of LST from Landsat-8 and MODIS data was implemented to generate the synthetic LST with Landsat-like spatial resolution and MODIS temporal information. The performance of pMSRAFM was tested and validated in the Heihe River Basin located in China. The results of six experiments showed that the fused LST was high similarity to the direct Landsat-derived LST with structural similarity index (SSIM) of 0.83 and the index of agreement (d) of 0.84. The range of SSIM was 0.65–0.88, the root mean square error (RMSE) yielded a range of 1.6–3.4 °C, and the averaged bias was 0.6 °C. Furthermore, the temporal information of MODIS LST was retained and optimized in the synthetic LST. The RMSE ranged from 0.7 °C to 1.5 °C with an average value of 1.1 °C. When compared with in situ LST observations, the mean absolute error and bias were reduced after fusion with the mean absolute bias of 1.3 °C. The validation results that fused LST possesses the spatial pattern of Landsat-derived LSTs and inherits most of the temporal properties of MODIS LSTs at the same time, so it can provide more accurate and credible information. Consequently, pMSRAFM can be served as a promising and practical fusion framework to prepare a high-quality LST spatiotemporal dataset for various applications in environment studies.

Download Full-text

SPATIAL AND TEMPORAL ANALYSIS OF MONTHLY WATER CONSUMPTION AND LAND SURFACE TEMPERATURE (LST) DERIVED USING LANDSAT 8 AND MODIS DATA

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-4-w19-193-2019 ◽

2019 ◽

Vol XLII-4/W19 ◽

pp. 193-198

Author(s):

R. Enriquez ◽

M. Rodriguez ◽

A. C. Blanco ◽

I. Estacio ◽

L. R. Depositario

Keyword(s):

Surface Temperature ◽

Spatial Resolution ◽

Land Surface Temperature ◽

Water Consumption ◽

Land Surface ◽

Urban Climate ◽

Temporal Analysis ◽

Urban Heat Islands ◽

Landsat 8 ◽

The Relationship

Abstract. Land Surface Temperature (LST) is one of the important factors in monitoring urban climate. Observing the variations of LST can provide a better understanding of the Urban Heat Islands (UHI) phenomenon. The aim of this research is to assess the relationship between the spatial and temporal distribution of LST and water consumption in Zamboanga City for years 2016 and 2017. Data from the city’s water district were used to compute for the per capita water consumption (PCWC) of 49 barangays. Landsat 8 LST data with 30m spatial resolution were computed using inverse Plank function and other parameters such as vegetation proportion and surface emissivity to assess LST spatially while MODIS Terra data with 1km spatial resolution were used to assess LST temporally. Result showed that Landsat LST and PCWC have moderate correlations with p < 0.01: 0.59 and 0.55 for March and April 2016, respectively; 0.49 and 0.56 for March and April 2017, respectively. These indicated that warmer barangays consumed more water. The temporal correlation of the MODIS LST and the computed PCWC equated a −0.71, p < 0.01, correlation. This negative correlation indicated that when LST increases, PCWC decreases, which do not directly indicate that the city consumed less water but rather that the supply was less during warmer months. It was evident as water rationing was experienced during the first quarter of 2016 and intensified on April where the highest LST was recorded. Finally, LST was found of good use in assessing the relationship of temperature and water consumption.

Download Full-text

EVAPOTRANSPIRATION ESTIMATION USING SSEBop METHOD WITH SENTINEL -2 AND LANDSAT-8 DATA SET

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-5-563-2018 ◽

2018 ◽

Vol XLII-5 ◽

pp. 563-566 ◽

Cited By ~ 2

Author(s):

D. N. Sharma ◽

V. Tare

Keyword(s):

Data Collection ◽

Surface Temperature ◽

Land Surface Temperature ◽

Land Surface ◽

Command Area ◽

Landsat 8 ◽

Ground Water Recharge ◽

Canal Command ◽

Canal Command Area ◽

Sentinel 2

Abstract. Estimation of evapotranspiration (ET) parameters is essential for understanding crop water requirements and to find out the ground water recharge. In situ data collection procedures are generally adopted to measure the parameters required to find ET. Latest remote sensing technologies accompanied by newly launched satellite datasets can supplement the field data collection and analysis by finding out some of the parameters such as land surface temperature, normalized difference vegetation index (NDVI), albedo, emissivity, etc. The Upper Ganga Canal Command Area (UGC) lying between two rivers Ganga and Yamuna situated between two states, namely Uttarakhand and Uttar Pradesh in North India is selected as the study area for this research work. Operational Simplified Surface Energy Balance (SSEBop) method is used to derive high resolution (10m) ET map for the Upper Ganga Canal Command Area. Sentinel-2 multi spectral images were used to derive land use, land cover (LU/LC) maps, NDVI, albedo, etc. Downscaled Landsat 8 images were used to derive land surface temperature of the command area. Meteorological data retrieved from the Indian Meteorological Department (IMD) was used to calculate reference evapotranspiration. ET map of the study area was generated using the above estimated parameters. Further, validation of the obtained ET values was accomplished by gridded ET data obtained from IMD.

Download Full-text