scholarly journals Glacier Facies Mapping Using a Machine-Learning Algorithm: The Parlung Zangbo Basin Case Study

2019 ◽  
Vol 11 (4) ◽  
pp. 452 ◽  
Author(s):  
Jingxiao Zhang ◽  
Li Jia ◽  
Massimo Menenti ◽  
Guangcheng Hu
Keyword(s):  
Machine Learning ◽  
Tibetan Plateau ◽  
Learning Algorithm ◽  
Remote Sensing Data ◽  
Landsat 8 ◽  
The Tibetan Plateau ◽  
Important Indicator ◽  
Very High Spatial Resolution ◽  
Multi Temporal ◽  
Elevation Model

Glaciers in the Tibetan Plateau are an important indicator of climate change. Automatic glacier facies mapping utilizing remote sensing data is challenging due to the spectral similarity of supraglacial debris and the adjacent bedrock. Most of the available glacier datasets do not provide the boundary of clean ice and debris-covered glacier facies, while debris-covered glacier facies play a key role in mass balance research. The aim of this study was to develop an automatic algorithm to distinguish ice cover types based on multi-temporal satellite data, and the algorithm was implemented in a subregion of the Parlung Zangbo basin in the southeastern Tibetan Plateau. The classification method was built upon an automated machine learning approach: Random Forest in combination with the analysis of topographic and textural features based on Landsat-8 imagery and multiple digital elevation model (DEM) data. Very high spatial resolution Gao Fen-1 (GF-1) Panchromatic and Multi-Spectral (PMS) imagery was used to select training samples and validate the classification results. In this study, all of the land cover types were classified with overall good performance using the proposed method. The results indicated that fully debris-covered glaciers accounted for approximately 20.7% of the total glacier area in this region and were mainly distributed at elevations between 4600 m and 4800 m above sea level (a.s.l.). Additionally, an analysis of the results clearly revealed that the proportion of small size glaciers (<1 km2) were 88.3% distributed at lower elevations compared to larger size glaciers (≥1 km2). In addition, the majority of glaciers (both in terms of glacier number and area) were characterized by a mean slope ranging between 20° and 30°, and 42.1% of glaciers had a northeast and north orientation in the Parlung Zangbo basin.

scholarly journals Combining Phenological Camera Photos and MODIS Reflectance Data to Predict GPP Daily Dynamics for Alpine Meadows on the Tibetan Plateau

2020 ◽  
Vol 12 (22) ◽  
pp. 3735
Author(s):  
Xuqiang Zhou ◽  
Xufeng Wang ◽  
Songlin Zhang ◽  
Yang Zhang ◽  
Xuejie Bai
Keyword(s):  
Tibetan Plateau ◽  
Eddy Covariance ◽  
Vegetation Index ◽  
Learning Algorithm ◽  
Gross Primary Production ◽  
Vegetation Indices ◽  
Remote Sensing Data ◽  
Estimation Accuracy ◽  
The Tibetan Plateau ◽  
Unit Space

Gross primary production (GPP) is the overall photosynthetic fixation of carbon per unit space and time. Due to uncertainties resulting from clouds, snow, aerosol, and topography, it is a challenging task to accurately estimate daily GPP. Daily digital photos from a phenological camera record vegetation daily greenness dynamics with little cloud or aerosol disturbance. It can be fused with satellite remote sensing data to improve daily GPP prediction accuracy. In this study, we combine the two types of datasets to improve the estimation accuracy of GPP for alpine meadow on the Tibetan Plateau. To examine the performance of different methods and vegetation indices (VIs), three experiments were designed. First, GPP was estimated with the light use efficiency (LUE) model with the green chromatic coordinate (GCC) from the phenological camera and vegetation index from MODIS, respectively. Second, GPP was estimated with the Backpropagation neural network machine learning algorithm (BNNA) method with GCC from the phenological camera and vegetation index from MODIS, respectively. Finally, GPP was estimated with the BNNA method using GCC and vegetation index as inputs at the same time. Compared with eddy covariance GPP, GPP predicted by the BNNA method with GCC and vegetation indices as inputs at the same time showed the highest accuracy of all the experiments. The results indicated that GCC had a higher accuracy than NDVI and EVI when only one vegetation index data was used in the LUE model or the BNNA method. The R2 of GPP estimated by BNNA and GPP from eddy covariance increased by 0.12 on average, RMSE decreased by 1.13 g C·m−2·day−1 on average, and MAD decreased by 0.87 g C·m−2·day−1 on average compared with GPP estimated by the traditional LUE model and GPP from eddy covariance. This study puts forth a new way to improve the estimation accuracy of GPP on the Tibetan Plateau. With the emergence of a large number of phenological cameras, this method has great potential for use on the Tibetan Plateau, which is heavily affected by clouds and snow.

scholarly journals Pattern of Turbidity Change in the Middle Reaches of the Yarlung Zangbo River, Southern Tibetan Plateau, from 2007 to 2017

2021 ◽  
Vol 13 (2) ◽  
pp. 182
Author(s):  
Ming Shen ◽  
Siyuan Wang ◽  
Yingkui Li ◽  
Maofeng Tang ◽  
Yuanxu Ma
Keyword(s):  
Tibetan Plateau ◽  
Satellite Imagery ◽  
Large Scale ◽  
Environmental Changes ◽  
Landsat 8 ◽  
The Tibetan Plateau ◽  
Important Indicator ◽  
Yarlung Zangbo River ◽  
Southern Tibetan Plateau

Turbidity is an important indicator of riverine conditions, especially in a fragile environment such as the Tibetan Plateau. Remote sensing, with the advantages of large-scale observations, has been widely applied to monitor turbidity change in lakes and rivers; however, few studies have focused on turbidity change of rivers on the Tibetan Plateau. We investigated the pattern of turbidity change in the middle reaches of the Yarlung Zangbo River, southern Tibetan Plateau, based on multispectral satellite imagery and in situ measurements. We developed empirical models from in situ measured water leaving reflectance and turbidity, and applied the best performed s-curve models on satellite imagery from Sentinel-2, Landsat 8, and Landsat 5 to derive turbidity change in 2007–2017. Our results revealed an overall decreasing spatial trend from the upper to lower streams. Seasonal variations were observed with high turbidity from July to September and low turbidity from October to May. Annual turbidity showed a temporally slightly declining trend from 2007 to 2017. The pattern of turbidity change is affected by the confluence of tributaries and the changes in precipitation and vegetation along the river. These findings provide important insights into the responses of riverine turbidity to climate and environmental changes on the Tibetan Plateau.

scholarly journals Assessing the Effect of Training Sampling Design on the Performance of Machine Learning Classifiers for Land Cover Mapping Using Multi-Temporal Remote Sensing Data and Google Earth Engine

2021 ◽  
Vol 13 (8) ◽  
pp. 1433
Author(s):  
Shobitha Shetty ◽  
Prasun Kumar Gupta ◽  
Mariana Belgiu ◽  
S. K. Srivastav
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Random Sampling ◽  
Sampling Design ◽  
Remote Sensing Data ◽  
Google Earth ◽  
Machine Learning Classifiers ◽  
Learning Classifiers ◽  
Multi Temporal ◽  
Google Earth Engine

Machine learning classifiers are being increasingly used nowadays for Land Use and Land Cover (LULC) mapping from remote sensing images. However, arriving at the right choice of classifier requires understanding the main factors influencing their performance. The present study investigated firstly the effect of training sampling design on the classification results obtained by Random Forest (RF) classifier and, secondly, it compared its performance with other machine learning classifiers for LULC mapping using multi-temporal satellite remote sensing data and the Google Earth Engine (GEE) platform. We evaluated the impact of three sampling methods, namely Stratified Equal Random Sampling (SRS(Eq)), Stratified Proportional Random Sampling (SRS(Prop)), and Stratified Systematic Sampling (SSS) upon the classification results obtained by the RF trained LULC model. Our results showed that the SRS(Prop) method favors major classes while achieving good overall accuracy. The SRS(Eq) method provides good class-level accuracies, even for minority classes, whereas the SSS method performs well for areas with large intra-class variability. Toward evaluating the performance of machine learning classifiers, RF outperformed Classification and Regression Trees (CART), Support Vector Machine (SVM), and Relevance Vector Machine (RVM) with a >95% confidence level. The performance of CART and SVM classifiers were found to be similar. RVM achieved good classification results with a limited number of training samples.

scholarly journals Mapping Allochemical Limestone Formations in Hazara, Pakistan Using Google Cloud Architecture: Application of Machine-Learning Algorithms on Multispectral Data

2021 ◽  
Vol 10 (2) ◽  
pp. 58
Author(s):  
Muhammad Fawad Akbar Khan ◽  
Khan Muhammad ◽  
Shahid Bashir ◽  
Shahab Ud Din ◽  
Muhammad Hanif
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Learning Algorithms ◽  
Remote Sensing Data ◽  
Kappa Coefficient ◽  
Machine Learning Algorithms ◽  
Landsat 8 ◽  
Sensing Data ◽  
Fossiliferous Limestone

Low-resolution Geological Survey of Pakistan (GSP) maps surrounding the region of interest show oolitic and fossiliferous limestone occurrences correspondingly in Samanasuk, Lockhart, and Margalla hill formations in the Hazara division, Pakistan. Machine-learning algorithms (MLAs) have been rarely applied to multispectral remote sensing data for differentiating between limestone formations formed due to different depositional environments, such as oolitic or fossiliferous. Unlike the previous studies that mostly report lithological classification of rock types having different chemical compositions by the MLAs, this paper aimed to investigate MLAs’ potential for mapping subclasses within the same lithology, i.e., limestone. Additionally, selecting appropriate data labels, training algorithms, hyperparameters, and remote sensing data sources were also investigated while applying these MLAs. In this paper, first, oolitic (Samanasuk), fossiliferous (Lockhart and Margalla) limestone-bearing formations along with the adjoining Hazara formation were mapped using random forest (RF), support vector machine (SVM), classification and regression tree (CART), and naïve Bayes (NB) MLAs. The RF algorithm reported the best accuracy of 83.28% and a Kappa coefficient of 0.78. To further improve the targeted allochemical limestone formation map, annotation labels were generated by the fusion of maps obtained from principal component analysis (PCA), decorrelation stretching (DS), X-means clustering applied to ASTER-L1T, Landsat-8, and Sentinel-2 datasets. These labels were used to train and validate SVM, CART, NB, and RF MLAs to obtain a binary classification map of limestone occurrences in the Hazara division, Pakistan using the Google Earth Engine (GEE) platform. The classification of Landsat-8 data by CART reported 99.63% accuracy, with a Kappa coefficient of 0.99, and was in good agreement with the field validation. This binary limestone map was further classified into oolitic (Samanasuk) and fossiliferous (Lockhart and Margalla) formations by all the four MLAs; in this case, RF surpassed all the other algorithms with an improved accuracy of 96.36%. This improvement can be attributed to better annotation, resulting in a binary limestone classification map, which formed a mask for improved classification of oolitic and fossiliferous limestone in the area.

scholarly journals In-Season Mapping of Irrigated Crops Using Landsat 8 and Sentinel-1 Time Series

2019 ◽  
Vol 11 (2) ◽  
pp. 118 ◽  
Author(s):  
Valérie Demarez ◽  
Florian Helen ◽  
Claire Marais-Sicre ◽  
Frédéric Baup
Keyword(s):  
Time Series ◽  
Shuttle Radar Topography Mission ◽  
Irrigation Scheduling ◽  
Landsat 8 ◽  
Radar Images ◽  
Optical Images ◽  
Multi Temporal ◽  
Irrigated Crops ◽  
Elevation Model ◽  
The Impact

Numerous studies have reported the use of multi-spectral and multi-temporal remote sensing images to map irrigated crops. Such maps are useful for water management. The recent availability of optical and radar image time series such as the Sentinel data offers new opportunities to map land cover with high spatial and temporal resolutions. Early identification of irrigated crops is of major importance for irrigation scheduling, but the cloud coverage might significantly reduce the number of available optical images, making crop identification difficult. SAR image time series such as those provided by Sentinel-1 offer the possibility of improving early crop mapping. This paper studies the impact of the Sentinel-1 images when used jointly with optical imagery (Landsat8) and a digital elevation model of the Shuttle Radar Topography Mission (SRTM). The study site is located in a temperate zone (southwest France) with irrigated maize crops. The classifier used is the Random Forest. The combined use of the different data (radar, optical, and SRTM) improves the early classifications of the irrigated crops (k = 0.89) compared to classifications obtained using each type of data separately (k = 0.84). The use of the DEM is significant for the early stages but becomes useless once crops have reached their full development. In conclusion, compared to a “full optical” approach, the “combined” method is more robust over time as radar images permit cloudy conditions to be overcome.

scholarly journals Understanding precipitation recycling over the Tibetan Plateau using tracer analysis with WRF

2020 ◽  
Vol 55 (9-10) ◽  
pp. 2921-2937
Author(s):  
Yanhong Gao ◽  
Fei Chen ◽  
Gonzalo Miguez-Macho ◽  
Xia Li
Keyword(s):  
Tibetan Plateau ◽  
Land Surface ◽  
Precipitation Amount ◽  
Interaction Strength ◽  
Convective Precipitation ◽  
High Mountain ◽  
The Tibetan Plateau ◽  
Important Indicator ◽  
Precipitation Recycling ◽  
Atmosphere Interaction

Abstract The precipitation recycling (PR) ratio is an important indicator that quantifies the land-atmosphere interaction strength in the Earth system’s water cycle. To better understand how the heterogeneous land surface in the Tibetan Plateau (TP) contributes to precipitation, we used the water-vapor tracer (WVT) method coupled with the Weather Research and Forecasting (WRF) regional climate model. The goals were to quantify the PR ratio, in terms of annual mean, seasonal variability and diurnal cycle, and to address the relationships of the PR ratio with lake treatments and precipitation amount. Simulations showed that the PR ratio increases from 0.1 in winter to 0.4 in summer when averaged over the TP with the maxima centered at the headwaters of three major rivers (Yangtze, Yellow and Mekong). For the central TP, the highest PR ratio rose to over 0.8 in August, indicating that most of the precipitation was recycled via local evapotranspiration in summer. The larger daily mean and standard deviation of the PR ratio in summer suggested a stronger effect of land-atmosphere interactions on precipitation in summer than in winter. Despite the relatively small spatial extent of inland lakes, the treatment of lakes in WRF significantly impacted the calculation of the PR ratio over the TP, and correcting lake temperature substantially improved both precipitation and PR ratio simulations. There was no clear relationship between PR ratio and precipitation amount; however, a significant positive correlation between PR and convective precipitation was revealed. This study is beneficial for the understanding of land-atmosphere interaction over high mountain regions.

scholarly journals Early warning of snow-caused disasters in pastoral areas on the Tibetan Plateau

2013 ◽  
Vol 13 (6) ◽  
pp. 1411-1425 ◽  
Author(s):  
W. Wang ◽  
T. Liang ◽  
X. Huang ◽  
Q. Feng ◽  
H. Xie ◽  
...  
Keyword(s):  
Tibetan Plateau ◽  
Early Warning ◽  
Model Development ◽  
Social Economy ◽  
Remote Sensing Data ◽  
Principal Component ◽  
The Tibetan Plateau ◽  
Qualitative Risk Assessment ◽  
Annual Probability ◽  
Warning Model

Abstract. This study develops a model for early warning of snow-caused livestock disasters on a county basis and proposes a method of qualitative risk assessment of snow disasters at 500 m resolution for pastoral areas on the Tibetan Plateau (TP). Data used for the model development include remote sensing data, statistical data of weather, livestock, and social economy, and 45 typical snow disaster cases from 2000 to 2010. The principal component analysis (PCA) approach is used to choose 7 crucial factors that contribute over 85% of information for early warning snow disasters on the TP. They are mean annual probability of snow disaster, number of snow-covered days, livestock stocking rate, continual days of mean daily temperature below −10 °C, grassland burial index, rate of snow-covered grassland, and per livestock gross domestic product. The chosen 411 cases from 2008 to 2010 are used to validate the prediction results from the developed early warning model, with an overall accuracy of 85.64% in predicting snow disasters and no disasters. This suggests that the early warning approach developed in the study has operational potential for predicting snow disasters on the TP.

Sign in / Sign up

Export Citation Format

Share Document