scholarly journals Spatiotemporal Fusion of Satellite Images via Very Deep Convolutional Networks

2019 ◽  
Vol 11 (22) ◽  
pp. 2701
Author(s):  
Yuhui Zheng ◽  
Huihui Song ◽  
Le Sun ◽  
Zebin Wu ◽  
Byeungwoo Jeon
Keyword(s):  
Remote Sensing ◽  
Sparse Representation ◽  
Remote Sensing Data ◽  
Linear Mapping ◽  
Image Features ◽  
Landsat Data ◽  
Fusion Model ◽  
Landsat Images ◽  
Sensing Data ◽  
Non Linear

Spatiotemporal fusion provides an effective way to fuse two types of remote sensing data featured by complementary spatial and temporal properties (typical representatives are Landsat and MODIS images) to generate fused data with both high spatial and temporal resolutions. This paper presents a very deep convolutional neural network (VDCN) based spatiotemporal fusion approach to effectively handle massive remote sensing data in practical applications. Compared with existing shallow learning methods, especially for the sparse representation based ones, the proposed VDCN-based model has the following merits: (1) explicitly correlating the MODIS and Landsat images by learning a non-linear mapping relationship; (2) automatically extracting effective image features; and (3) unifying the feature extraction, non-linear mapping, and image reconstruction into one optimization framework. In the training stage, we train a non-linear mapping between downsampled Landsat and MODIS data using VDCN, and then we train a multi-scale super-resolution (MSSR) VDCN between the original Landsat and downsampled Landsat data. The prediction procedure contains three layers, where each layer consists of a VDCN-based prediction and a fusion model. These layers achieve non-linear mapping from MODIS to downsampled Landsat data, the two-times SR of downsampled Landsat data, and the five-times SR of downsampled Landsat data, successively. Extensive evaluations are executed on two groups of commonly used Landsat–MODIS benchmark datasets. For the fusion results, the quantitative evaluations on all prediction dates and the visual effect on one key date demonstrate that the proposed approach achieves more accurate fusion results than sparse representation based methods.

Using 250-m MODIS Data for Enhancing Spatiotemporal Fusion by Sparse Representation

2020 ◽  
Vol 86 (6) ◽  
pp. 383-392
Author(s):  
Liguo Wang ◽  
Xiaoyi Wang ◽  
Qunming Wang
Keyword(s):  
Remote Sensing ◽  
Sparse Representation ◽  
Spatial Resolution ◽  
Temporal Resolution ◽  
Remote Sensing Data ◽  
Landsat Data ◽  
Sensing Data ◽  
Modis Data ◽  
Fine Spatial Resolution ◽  
Fusion Methods

Spatiotemporal fusion is an important technique to solve the problem of incompatibility between the temporal and spatial resolution of remote sensing data. In this article, we studied the fusion of Landsat data with fine spatial resolution but coarse temporal resolution and Moderate Resolution Imaging Spectroradiometer (MODIS) data with coarse spatial resolution but fine temporal resolution. The goal of fusion is to produce time-series data with the fine spatial resolution of Landsat and the fine temporal resolution of MODIS. In recent years, learning-based spatiotemporal fusion methods, in particular the sparse representation-based spatiotemporal reflectance fusion model (SPSTFM), have gained increasing attention because of their great restoration ability for heterogeneous landscapes. However, remote sensing data from different sensors differ greatly on spatial resolution, which limits the performance of the spatiotemporal fusion methods (including SPSTFM) to some extent. In order to increase the accuracy of spatiotemporal fusion, in this article we used existing 250-m MODISbands (i.e., red and near-infrared bands) to downscale the observed 500-m MODIS bands to 250 m before SPTSFM-based fusion of MODIS and Landsat data. The experimental results show that the fusion accuracy of SPTSFM is increased when using 250-m MODIS data, and the accuracy of SPSTFM coupled with 250-m MODIS data is greater than the compared benchmark methods.

scholarly journals Estimation of soil types by non linear analysis of remote sensing data

2008 ◽  
Vol 15 (1) ◽  
pp. 115-126 ◽  
Author(s):  
C. Hahn ◽  
R. Gloaguen
Keyword(s):  
Remote Sensing ◽  
Soil Type ◽  
Remote Sensing Data ◽  
Soil Types ◽  
Support Vector ◽  
Sensing Data ◽  
Vector Machines ◽  
Non Linear ◽  
Input Variables ◽  
Type Classification

Abstract. The knowledge of soil type and soil texture is crucial for environmental monitoring purpose and risk assessment. Unfortunately, their mapping using classical techniques is time consuming and costly. We present here a way to estimate soil types based on limited field observations and remote sensing data. Due to the fact that the relation between the soil types and the considered attributes that were extracted from remote sensing data is expected to be non-linear, we apply Support Vector Machines (SVM) for soil type classification. Special attention is drawn to different training site distributions and the kind of input variables. We show that SVM based on carefully selected input variables proved to be an appropriate method for soil type estimation.

scholarly journals CREATION OF GIS-RESOURCES FOR PHYSIOGRAPHIC ZONING OF THE TRANSBOUNDARY RUSSIAN-MONGOLIAN TERRITORY

2021 ◽  
Vol 26 (2) ◽  
pp. 91-102
Author(s):  
Andrew N. Beshentsev ◽  
◽  
Alexander A. Ayurzhanaev ◽  
Bator V. Sodnomov ◽  
◽  
...  
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Data ◽  
Landsat Images ◽  
Statistical Research ◽  
Active Biomass ◽  
Sensing Data ◽  
Digital Elevation ◽  
Geographical Regions ◽  
Elevation Model ◽  
Geographical Characteristics

The article is aimed at the development of methodological foundations for the creation of geoin-formation resources of transboundary territories based on cartographic materials and remote sensing data, as well as physical and geographical zoning of the transboundary Russian-Mongolian territory. The methodological basis of the study is cartographic and statistical research methods, geoinformation technology, as well as processing and analysis of remote sensing data. As a result, the study deter-mines the features of geoinformation resources, presents their characteristics, develops a classification and substantiates their integrating value in making interstate territorial decisions. The article gives the physical and geographical characteristics of the territory, determines the scale of mapping, establishes the basic units of geoinformation mapping and modeling, creates the coverage of the basin division, and proposes a scheme for creating basic geoinformation resources for the physical and geographical zoning of the territory. Based on the analysis of the digital elevation model, the territory was zoned according to the morphometric parameters of the relief. As a result of processing and analysis of Landsat images at different times, the territory was zoned in terms of the amount of photosynthetically active biomass (NDVI). As a result of zoning, 6 physical-geographical regions and 33 physical-geographical areas were identified.

scholarly journals Modeling regional evaporation through ANFIS incorporated solely with remote sensing data

2013 ◽  
Vol 10 (5) ◽  
pp. 6153-6192
Author(s):  
F.-J. Chang ◽  
W. Sun
Keyword(s):  
Remote Sensing ◽  
Land Surface ◽  
Vegetation Index ◽  
Remote Sensing Data ◽  
Data Allocation ◽  
Remotely Sensed Data ◽  
Estimation Model ◽  
Landsat Images ◽  
Inference System ◽  
Sensing Data

Abstract. The study aims to model regional evaporation that possesses the ability to present the spatial distribution of evaporation across the whole Taiwan by the adaptive network-based fuzzy inference system (ANFIS) based solely on remote sensing data. The remote sensing data used in this study consist of Landsat image products including Enhanced Vegetation Index (EVI) and land surface temperature (LST). The model construction is designed through two types of data allocation (temporal and spatial) driven with the same ten-year data of EVI and LST derived from Landsat images. Evidences indicate the estimation model based solely on remotely sensed data can effectively detect the spatial variation of evaporation and appropriately capture the evaporation trend with acceptable errors of about 1 mm day−1. The results also demonstrate the composite of EVI and LST input to the proposed estimation model improves the accuracy of estimated evaporation values as compared with the model using LST as the only input, which reveals EVI indeed benefits the estimation process. The results suggest Model-T (temporal input allocation) is suitable for making island-wide evaporation estimation while Model-S (spatial input allocation) is suitable for making evaporation estimation at ungauged sites. An island-wide evaporation map for the whole study area (Taiwan Island) is then derived. It concludes the proposed ANFIS model incorporated solely with remote sensing data can reasonably well generate evaporation estimation and is reliable as well as easily applicable for operational estimation of evaporation over large areas where the network of ground-based meteorological gauging stations is not dense enough or readily available.

scholarly journals The Impact of Coal Exploitation on Tidal Flat Changes, an Investigation Using Remote Sensing Data in Vietnam

2021 ◽  
Vol 1 (2) ◽  
Author(s):  
Thi Lan PHAM ◽  
Si Son TONG ◽  
Thi Thu Ha LE ◽  
Thi Le LE ◽  
Huu Duc HOANG
Keyword(s):  
Remote Sensing ◽  
Coal Mining ◽  
Coal Mine ◽  
Tidal Flat ◽  
Remote Sensing Data ◽  
Tidal Flats ◽  
Mining Activities ◽  
Landsat Images ◽  
Sensing Data ◽  
The Impact

Tidal flat plays a crucial role in socio-economic development and ecological environment.Tidal flats in Ha Long-Cam Pha in Vietnam are impacted by human activities, especially coal miningactivities. Using remote sensing data is able to detect, extract, and monitor the changes of tidal flats andexploited coal mine area with multi-temporal, in various scales, and for a large coverage. This studyaims to investigate the impact of coal mining activities on the changes of tidal flats using remote sensingin Cam Pha, Ha Long, one of the biggest coal basins in Vietnam. Digital Elevation Models (DEMs) oftidal flats constructed by Landsat satellite images acquired in years 1989, 2001, and 2014 are comparedto determine the volume changes. Besides, coal mining activities including coal production, waste rockdump area, and the expansion of open coal mine during the period 1989-2014 are investigated usingcorrespondent Landsat images and the reports from the coal mine companies in the study area. Sedimentsamples in tidal flats are analyzed to determine the origin of the sediments. As the results, organic matterin the tidal flats is dominant with the concentration of 459 g/kg to 607 g/kg, which is evidence for theimpact of coal exploitation on the coastal environment. In addition, the relationship between coal mineactivities and tidal flat variation is well observed in this study.

scholarly journals Mapping Forest Canopy Height in Mountainous Areas Using ZiYuan-3 Stereo Images and Landsat Data

Forests ◽  
2019 ◽  
Vol 10 (2) ◽  
pp. 105 ◽  
Author(s):  
Mingbo Liu ◽  
Chunxiang Cao ◽  
Yongfeng Dang ◽  
Xiliang Ni
Keyword(s):  
Remote Sensing ◽  
Forest Canopy ◽  
Remote Sensing Data ◽  
Canopy Height ◽  
Landsat 8 ◽  
Surface Reflectance ◽  
Landsat Data ◽  
Sensing Data ◽  
Forest Height ◽  
Reflectance Data

Forest canopy height is an important parameter for studying biodiversity and the carbon cycle. A variety of techniques for mapping forest height using remote sensing data have been successfully developed in recent years. However, the demands for forest height mapping in practical applications are often not met, due to the lack of corresponding remote sensing data. In such cases, it would be useful to exploit the latest, cheaper datasets and combine them with free datasets for the mapping of forest canopy height. In this study, we proposed a method that combined ZiYuan-3 (ZY-3) stereo images, Shuttle Radar Topography Mission global 1 arc second data (SRTMGL1), and Landsat 8 Operational Land Imager (OLI) surface reflectance data. The method consisted of three procedures: First, we extracted a digital surface model (DSM) from the ZY-3, using photogrammetry methods and subtracted the SRTMGL1 to obtain a crude canopy height model (CHM). Second, we refined the crude CHM and correlated it with the topographically corrected Landsat 8 surface reflectance data, the vegetation indices, and the forest types through a Random Forest model. Third, we extrapolated the model to the entire study area covered by the Landsat data, and obtained a wall-to-wall forest canopy height product with 30 m × 30 m spatial resolution. The performance of the model was evaluated by the Random Forest’s out-of-bag estimation, which yielded a coefficient of determination (R2) of 0.53 and a root mean square error (RMSE) of 3.28 m. We validated the predicted forest canopy height using the mean forest height measured in the field survey plots. The validation result showed an R2 of 0.62 and a RMSE of 2.64 m.

scholarly journals Exploring the Relationship between LST, LULC and NDVI in Saïss Plain using Geospatial Techniques

2021 ◽  
Vol 314 ◽  
pp. 04001
Author(s):  
Manal El Garouani ◽  
Mhamed Amyay ◽  
Abderrahim Lahrach ◽  
Hassane Jarar Oulidi
Keyword(s):  
Remote Sensing ◽  
Surface Temperature ◽  
Land Surface Temperature ◽  
Land Surface ◽  
Vegetation Index ◽  
Arable Land ◽  
Remote Sensing Data ◽  
Landsat Images ◽  
Gis And Remote Sensing ◽  
Sensing Data

Land use/land cover (LULC) change has been confirmed that have a significant impact on climate through various pathways that modulate land surface temperature (LST) and precipitation. However, there are no studies illustrated this link in the Saïss plain using remote sensing data. Thus, the aim of this study is to monitor the LST relationship between LULC and vegetation index change in the Saïss plain using GIS and Remote Sensing Data. We used 18 Landsat images to study the annual and interannual variation of LST with LULC (1988, 1999, 2009 and 2019). To highlight the effect of biomass on LST distribution, the Normalized Difference Vegetation Index (NDVI) was calculated, which is a very good indicator of biomass. The mapping results showed an increase in the arboriculture and urbanized areas to detriment of arable lands and rangelands. Based on statistical analyzes, the LST varies during the phases of plant growth in all seasons and that it is diversified due to the positional influence of LULC type. The variation of land surface temperature with NDVI shows a negative correlation. This explains the increase in the surface temperature in rangelands and arable land while it decreases in irrigated crops and arboriculture.

Sign in / Sign up

Export Citation Format

Share Document