•A CNN-based approach was applied to map the landslide susceptibility.•A novel multiscale sampling strategy was proposed to generate the training data.•Three machine learning methods were applied for ...comparison.•CNN trained with multiscale fusion data can generate accurate and reliable results.
Landslides are one of the most widespread natural disasters and pose severe threats to people, properties, and the environment in many areas. Landslide susceptibility mapping (LSM) has proven useful in designing landslide mitigation strategies for reducing disaster risk and societal and economic losses, which are essential for land use planning, hazard prevention, and risk management. Recent efforts for improving accuracies of LSM have focused on the utilization of convolutional neural network (CNN) in some image-related tasks, however, due to the inconsistency of data representation, CNN-related studies need to be further explored. In this study, a CNN-based approach for LSM was proposed and experimentally applied in a Jiuzhaigou region where a catastrophic earthquake taken place on 8 August 2017, in Sichuan, China. To address the issue of data representation in the CNN model, we proposed a multiscale sampling strategy which to our knowledge is novel in LSM. In this way, the multiscale training samples (i.e., small scale, medium scale and large scale) were generated from the selected eleven landslide causative factors. The success-rate curve (SRC) and prediction-rate curve (PRC) were applied to validate the LSM results, and three conventional machine learning algorithms, i.e., logistic regression, multi-layer perceptron (MLP) neural network and radial basis function (RBF) neural network, were attempted for comparison. Specifically, MLP neural network achieved the best performance among three machine learning methods, with the area under the SRC (AU-SRC) and PRC (AU-PRC) values of 81.18% and 82.84%, respectively. Nevertheless, the AU-SRC and AU-PRC values of CNN-based approach reached to 97.45% and 88.02%, which were about 16% and 6% higher than that of the MLP neural network, respectively. The present study demonstrated both the excellent goodness-of-fit and strong prediction ability of CNN-based approach for LSM, which also showed the effectiveness and feasibility of the proposed multiscale sampling strategy. Additionally, present study revealed that the spatial data close to the landslide location might be more suitable to predict the probability of the landslide occurrence. Finally, we expect that the deep learning method based on multiscale data representation will advance our ability to assess the landslide susceptibility and raise the awareness of landslide disasters.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Accurate landslide detection and mapping are essential for land use planning, management/assessment, and geo-disaster risk mitigation as well as post-disaster reconstructions. Till now, visual ...interpretation and field survey are still the most widely adopted techniques for landslide mapping, which are often criticized labor-intensive, time-consuming, and costly. With the rapid advancement of artificial intelligence, deep-learning-based approach for landslide detection and mapping has drawn great attention for its significant advantages over the traditional techniques. However, lack of sufficient training samples has constrained the application of deep-learning-based approach in landslide detection from satellite images for a long time. The present study aimed to examine the feasibility of a new deep-learning-based approach to intelligently detect and map earthquake-triggered landslides from single-temporal RapidEye satellite images. Specifically, the proposed approach consists of three steps. First of all, a standard data preprocessing workflow to automatically generate training samples was designed and some data augmentation strategies were implemented to alleviate the lack of training samples. Then, a cascaded end-to-end deep learning network, namely LandsNet, was constructed to learn various features of landslides. Finally, the identified landslide maps were further optimized with morphological processing. Experiments in two spatially independent earthquake-affected regions showed our proposed approach yielded the best F1 value of about 86.89%, which was about 7% and 8% higher than that obtained by ResUNet and DeepUNet, respectively. Comparative studies on the feasibility and robustness of the proposed approach with ResUNet and DeepUNet demonstrated its strong application potentials in the emergency response of natural disasters.
Influences of climatic change and anthropogenic activities on the terrestrial water storage (TWS) change are significant in the mid- and high-latitude areas. Since 2002, the Gravity Recovery and ...Climate Experiment (GRACE) satellite mission has provided quantitative measurements of TWS changes with unprecedented accuracy at global, regional and basin scales. In this study, the noise level of various GRACE-derived TWS anomalies (TWSA) data were evaluated by using a generalized three-cornered hat (GTCH) method. A time-dependent weights approach was adopted to obtain a combined TWSA series over the Songhua River Basin (SRB) from 2003 to 2013. Monthly TWSA data during the past decades (1982–2002) were reconstructed by using an artificial neural network (ANN) approach with the good performance evaluated by the correlation coefficient of 0.89 and the Nash-Sutcliff efficiency of 0.79 over the study region. In-situ groundwater level measurements were used for validation of the groundwater storage (GWS) changes (estimated by using GRACE-derived TWS changes in association with the other simulated components of water storage changes from land surface models (LSMs)). The primary driving factors of spatiotemporal variations of GWS, as well as their inter-/intra-annually varying characteristics, were explored. The present study revealed that the variations of GWS featured a “downward fluctuations” (1982–1994), “stable upward” (1998–2008) and “decreasing dramatically” (2009–2013) period, respectively, over the SRB. In general, GWS had varied in a steady decline trend at a decreasing rate of 1.04 ± 0.59 mm year−1 from 1982 to 1994. With the enhanced climatic and anthropogenic influences over the region since 2000, several severe fluctuations characterized the GWS variations with occurrences of spring droughts and flooding over the region, which suggested significant effects of global changes posed on GWS variations of the region.
Display omitted
•Several GRACE solutions were evaluated and combined.•Longer-term groundwater storage variations were hindcasted by using the ANN model.•Long-term spatial-temporal variations of groundwater storage were analyzed.•The dominant driving factors for groundwater storage changes were explored.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
In Punjab (Pakistan), the increasing population and expansion of land use for agriculture have severely exploited the regional groundwater resources. Intensive pumping has resulted in a rapid decline ...in the level of the water table as well as its quality. Better management practices and artificial recharge are needed for the development of sustainable groundwater resources. This study proposes a methodology to delineate favorable groundwater potential recharge zones (FPRI) by integrating maps of groundwater potential recharge index (PRI) with the DRASTIC-based groundwater vulnerability index (VI). In order to evaluate both indexes, different thematic layers corresponding to each index were overlaid in ArcGIS. In the overlay analysis, the weights (for various thematic layers) and rating values (for sub-classes) were allocated based on a review of published literature. Both were then normalized and modified using the analytical hierarchical process (AHP) and a frequency ratio model respectively. After evaluating PRI and FPRI, these maps were validated using the area under the curve (AUC) method. The PRI map indicates that 53% of the area assessed exists in very low to low recharge zones, 22% in moderate, and 25% in high to excellent potential recharge zones. The VI map indicates that 38% of the area assessed exists in very low to low vulnerability, 33% in moderate, and 29% in high to very high vulnerability zones. The FPRI map shows that the central region of Punjab is moderately-to-highly favorable for recharge due to its low vulnerability and high recharge potential. During the validation process, it was found that the AUC estimated with modified weights and rating values was 79% and 67%, for PRI and VI indexes, respectively. The AUC was less when evaluated using original weights and rating values taken from published literature. Maps of favorable groundwater potential recharge zones are helpful for planning and implementation of wells and hydraulic structures in this region.
Display omitted
•Remotely derived maps and conventional data are helpful in mapping recharge zones.•Probability frequency ratio is preferred to allocate highly validated rating values.•Analytical hierarchical process is multi-criterion approach for weightage allocation.•Recharge potential and vulnerability help evaluate favorable recharge zones.•The area under the curve approach can be used to validate maps.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Urban building segmentation is a prevalent research domain for very high resolution (VHR) remote sensing; however, various appearances and complicated background of VHR remote sensing imagery make ...accurate semantic segmentation of urban buildings a challenge in relevant applications. Following the basic architecture of U-Net, an end-to-end deep convolutional neural network (denoted as DeepResUnet) was proposed, which can effectively perform urban building segmentation at pixel scale from VHR imagery and generate accurate segmentation results. The method contains two sub-networks: One is a cascade down-sampling network for extracting feature maps of buildings from the VHR image, and the other is an up-sampling network for reconstructing those extracted feature maps back to the same size of the input VHR image. The deep residual learning approach was adopted to facilitate training in order to alleviate the degradation problem that often occurred in the model training process. The proposed DeepResUnet was tested with aerial images with a spatial resolution of 0.075 m and was compared in performance under the exact same conditions with six other state-of-the-art networks—FCN-8s, SegNet, DeconvNet, U-Net, ResUNet and DeepUNet. Results of extensive experiments indicated that the proposed DeepResUnet outperformed the other six existing networks in semantic segmentation of urban buildings in terms of visual and quantitative evaluation, especially in labeling irregular-shape and small-size buildings with higher accuracy and entirety. Compared with the U-Net, the F1 score, Kappa coefficient and overall accuracy of DeepResUnet were improved by 3.52%, 4.67% and 1.72%, respectively. Moreover, the proposed DeepResUnet required much fewer parameters than the U-Net, highlighting its significant improvement among U-Net applications. Nevertheless, the inference time of DeepResUnet is slightly longer than that of the U-Net, which is subject to further improvement.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Landslide susceptibility mapping is an effective approach for landslide risk prevention and assessments. The occurrence of slope instability is highly correlated with intrinsic variables that ...contribute to the occurrence of landslides, such as geology, geomorphology, climate, hydrology, etc. However, feature selection of those conditioning factors to constitute datasets with optimal predictive capability effectively and accurately is still an open question. The present study aims to examine further the integration of the selected landslide conditioning factors with Q-statistic in Geo-detector for determining stratification and selection of landslide conditioning factors in landslide risk analysis as to ultimately optimize landslide susceptibility model prediction. The location chosen for the study was Atsuma Town, which suffered from landslides following the Eastern Iburi Earthquake in 2018 in Hokkaido, Japan. A total of 13 conditioning factors were obtained from different sources belonging to six categories: geology, geomorphology, seismology, hydrology, land cover/use and human activity; these were selected to generate the datasets for landslide susceptibility mapping. The original datasets of landslide conditioning factors were analyzed with Q-statistic in Geo-detector to examine their explanatory powers regarding the occurrence of landslides. A Random Forest (RF) model was adopted for landslide susceptibility mapping. Subsequently, four subsets, including the Manually delineated landslide Points with 9 features Dataset (MPD9), the Randomly delineated landslide Points with 9 features Dataset (RPD9), the Manually delineated landslide Points with 13 features Dataset (MPD13), and the Randomly delineated landslide Points with 13 features Dataset (RPD13), were selected by an analysis of Q-statistic for training and validating the Geo-detector-RF- integrated model. Overall, using dataset MPD9, the Geo-detector-RF-integrated model yielded the highest prediction accuracy (89.90%), followed by using dataset MPD13 (89.53%), dataset RPD13 (88.63%) and dataset RPD9 (87.07%), which implied that optimized conditioning factors can effectively improve the prediction accuracy of landslide susceptibility mapping.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Influences of the increasing pressure of climate change and anthropogenic activities on wetlands ecosystems and agriculture are significant around the world. This paper assessed the spatiotemporal ...land use and land cover changes (LULCC), especially for conversion from marshland to other LULC types (e.g., croplands) over the Songnen and Sanjiang Plain (SNP and SJP), northeast China, during the past 35 years (1980–2015). The relative role of human activities and climatic changes in terms of their impacts on wetlands and agriculture dynamics were quantitatively distinguished and evaluated in different periods based on a seven-stage LULC dataset. Our results indicated that human activities, such as population expansion and socioeconomic development, and institutional policies related to wetlands and agriculture were the main driving forces for LULCC of the SJP and SNP during the past decades, while increasing contributions of climatic changes were also found. Furthermore, as few studies have identified which geographic regions are most at risk, how the future climate changes will spatially and temporally impact wetlands and agriculture, i.e., the suitability of wetlands and agriculture distributions under different future climate change scenarios, were predicted and analyzed using a habitat distribution model (Maxent) at the pixel-scale. The present findings can provide valuable references for policy makers on regional sustainability for food security, water resource rational management, agricultural planning and wetland protection as well as restoration of the region.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Display omitted
•The wetland landscape types in the Liao River Estuary fluctuated frequently.•Human activities increased the fragmentation and spatial heterogeneity of wetland.•Water salinity ...regulated the Suaeda salsa growth in the Liao River Estuary wetland.•River discharge and precipitation altered the Suaeda salsa area by reducing salinity.
Coastal wetlands are important ecosystems that connect land to open sea, and their service functions are important in estuaries globally. Using long time series of remotely sensed information, transfer matrix and direction of landscape types from 1986 to 2020 in the coastal wetlands of the Liao River Estuary (LRE) were selected to investigate landscape pattern changes. And the dynamic response of Suaeda salsa (S. salsa) to hydro-climatic factors were explored using partial correlation and nonlinear analysis. The results suggested that landscape fragmentation and abundance have increased with frequent disturbance in the LRE over the last three decades, and more than 60 % of S. salsa, tidal flats, and water transitioned into buildings, farmland, and Phragmites australis (P. australis) in the study area. Further analyses of dynamic response of landscape metrics to influence factors indicated that the main drivers forcing landscape pattern changes in coastal wetlands in the LRE were socio-economic factors, followed by natural factors. The S. salsa spatial variations were positively correlated with river discharge and precipitation but without significant correlation with temperature in the early growing stages of vegetation (P < 0.05) in the coastal wetlands of the LRE, which implied that S. salsa growth mainly relies on river discharge and precipitation by reducing water salinity. Present study may provide new insights into restoration guidance and environmental management for coastal wetland protection.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
High-quality soil moisture (SM) estimation is crucial for various applications, including drought monitoring, environmental assessment, and agricultural management. Advances in remote sensing ...technology have enabled the retrieval of near real-time Earth surface SM using both active and passive sensors. However, the ESA climate change initiative (CCI) SM product, which combines data from multiple sensors, sacrifices spatial-temporal resolution and coverage due to satellite orbit constraints and retrieval algorithms. To address this issue, an SM reconstruction approach based on a conditional variational autoencoder model was developed, leveraging the high spatial resolution of SMAP L4 data and the accuracy of CCI fused products across different land cover types. This method resulted in the creation of a global three-day SM product at 0.0625<inline-formula><tex-math notation="LaTeX">^{\circ }</tex-math></inline-formula> spanning from 2015 to 2021. The reconstructed SM product underwent rigorous validation against global core SM sites and sparse observation networks. The evaluation employed multiple metrics, including the global unbiased root mean square error (ubRMSE) and correlation coefficient (CC). The validation yielded results, with ubRMSE values of approximately 0.029 and 0.071 m<inline-formula><tex-math notation="LaTeX">^{3}</tex-math></inline-formula>/m<inline-formula><tex-math notation="LaTeX">^{3}</tex-math></inline-formula>, and CC values of around 0.863 and 0.743 for core SM sites and sparse observation networks. This reconstructed product offers global coverage and enhanced accuracy compared to existing benchmarks.
To obtain independent, consecutive, and high-resolution precipitation data, the four-dimensional variational (4D-Var) method was applied to directly assimilate satellite precipitation products into ...the Weather Research and Forecasting (WRF) model. The precipitation products of the Tropical Rainfall Measuring Mission 3B42 (TRMM 3B42) and its successor, the Integrated Multi-satellitE Retrievals for Global Precipitation Measurement (GPM IMERG) were assimilated in this study. Two heavy precipitation events that occurred over the Huaihe River basin in eastern China were studied. Before assimilation, the WRF model simulations were first performed with different forcing data to select more suitable forcing data and determine the control experiments for the subsequent assimilation experiments. Then, TRMM 3B42 and GPM IMERG were separately assimilated into the WRF. The simulated precipitation results in the outer domain (D01), with a 27-km resolution, and the inner domain (D02), with a 9-km resolution, were evaluated in detail. The assessments showed that (1) 4D-Var with TRMM 3B42 or GPM IMERG could both significantly improve WRF precipitation predictions at a time interval of approximately 12 h; (2) the WRF simulated precipitation assimilated with GPM IMERG outperformed the one with TRMM 3B42; (3) for the WRF output precipitation assimilated with GPM IMERG over D02, which has spatiotemporal resolutions of 9 km and 50 s, the correlation coefficients of the studied events in August and November were 0.74 and 0.51, respectively, at the point and daily scales, and the mean Heidke skill scores for the two studied events both reached 0.31 at the grid and hourly scales. This study can provide references for the assimilation of TRMM 3B42 or GPM IMERG into the WRF model using 4D-Var, which is especially valuable for hydrological applications of GPM IMERG during the transition period from the TRMM era into the GPM era.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK