Landslide Detection Research Articles

Rancang Bangun Alat Deteksi Tanah Longsor Berbasis IoT dengan NodeMCU ESP8266 dan MPU6050

Landslide is a geological process caused by the displacement of rock and soil mass. In general, landslides are caused by geographical conditions in the form of mountains and slopes as well as high rainfall which causes the soil to become unstable. This study aims to make a landslide detection tool using NodeMCU ESP8266 as a microcontroller and MPU6050 as a sensor so that it can detect the acceleration of the earth on the x, y, and z axes and the slope of the ground. This landslide detection tool is based on the Internet of Things (IoT) so that it allows the acceleration of the earth and the slope of the ground to be monitored in real-time. This tool is linked to applications built using cloud services on a real-time database of firebase and MIT APP Inventor to build applications. From this study, it can be concluded that landslide detection tools and applications can work according to the design that is able to display the acceleration of movement and slope of the ground in real-time and can convey the condition status, namely safe, beware and alert with an average error of 0.419%

A prototype model for detection and classification of landslides using satellite data

Landslides are natural and manmade disasters that cause threat to human life and lead to huge economic loss. Last few decade number of approaches have been developed for early detection of landslide for protecting life and saving properties. This paper proposes a prototype for an artificial intelligent model to detect and predict different types of landslides in hilly area with remote sensing techniques. All developing countries are following a steep increase in development of infrastructure like buildings, roads tunnels bridges railway tracks. Demand of connecting remote area is very high but on other side of environment it is also true that high demand of construction in morpho material area is causing many disasters like landslide. Landslide causes the loss of property and life so an early alarming will be help full for disaster management. Remotely sensed data pre-processed with artificial intelligent technologies will be helpful for landslide detection, creating landslide susceptibility map and inventory. Focus of this study is on enhancing the accuracy to detect landslide, list out the different features for extraction from satellite images and pre processing steps. This research also focuses on application of robust early prediction of type of landslide. This research will help in detection of landslide early to protect economical losses and human lives.

Disaster Monitoring based on IoT and Long Range Assisted Framework

We encounter so many hazardous situations which effects living species and the materials they own. Due to natural calamities and environmental disasters, there is an increase in losses of lives and materials. Landslides are caused due to heavy rains, sloping of land because of earthquakes and deforestation. The research is about the preventive landslide detection and alerting system using various sensors and Arduino. The data collected by the sensors is transferred to Arduino which is further sent to NODEMCU through Lora module. The data obtained at NODEMCU will be transferred to database server for real-time monitoring and processing. Due improvement in the field of IoT systems has made the use of low cost, low power LoRA technologies to detect the environmental disaster and prevent from dangerous situations with less damage to living beings. In view to cover larger area with reduced costs and low power consumption, we used the LoRa technology for transmitting the monitoring data and Wi-Fi communication is used for sending the alerts. The processed data will be displayed on the mobile application interface.

Soil mass movement monitoring for landslide detection using low-cost accelerometer sensor as inclinometer

This paper presents soil mass movement monitoring for landslides detection using low-cost MEMS accelerometer as inclinometer. Commercial inclinometers for geotechnical ground observations are quite expensive. This research aims to study and develop low-cost inclinometer as an alternative using accelerometer. The output of the low-cost accelerometer is noisy and fluctuated make it not suitable for accurate measurement device. We solved this problem in this paper using moving average filter. The digital filter algorithm was tested and showed promising results.

Remote Sensing Application for Landslide Detection, Monitoring along Eastern Lake Michigan (Miami Park, MI)

We assessed the nature and spatial and temporal patterns of deformation over the Miami Park bluffs on the eastern margin of Lake Michigan and investigated the factors controlling its observed deformation. Our approach involved the following steps: (1) extracting bluff deformation rates (velocities along the line of sight of the satellite) using a stack of Sentinel-1A radar imagery in ascending acquisition geometry acquired between 2017 and 2021 and applying the Intermittent Small Baseline Subset (ISBAS) InSAR time series analysis method; (2) generating high-resolution (5 cm) elevation models and orthophotos from temporal unmanned aerial vehicle (UAV) surveys acquired in 2017, 2019, and 2021; and (3) comparing the temporal variations in mass wasting events to other relevant datasets including the ISBAS-based bluff deformation time series, lake level (LL) variations, and local glacial stratigraphy. We identified areas witnessing high line-of-sight (LOS) deformation rates (up to −21 mm/year) along the bluff from the ISBAS analysis and seasonal deformation patterns associated with freeze-thaw cycles, suggesting a causal effect. The acceleration of slope failures detected from field and UAV acquisitions correlated with high LLs and intensified onshore wave energy in 2020. The adopted methodology successfully predicts landslides caused by freezes and thaws of the slope face by identifying prolonged slow deformation preceding slope failures, but it does not predict the catastrophic landslides preceded by short-lived LOS deformation related to LL rise.

Wide Area Detection and Distribution Characteristics of Landslides along Sichuan Expressways

Wide area landslide detection is a major international research hotspot in the field of geological hazards, and the integration of multi-temporal optical satellite images and spaceborne interferometric synthetic aperture radar (InSAR) appears to be an effective way to realize this. In this paper, a technical framework is presented for wide area landslide detection: (i) multi-temporal satellite optical images are used to detect landslides with distinguishable geomorphological features; (ii) Generic Atmospheric Correction Online Service (GACOS) assisted InSAR stacking is employed to generate annual surface displacement rate maps in radar line of sight using satellite SAR images from both ascending and descending tracks, which are in turn utilized to automatically detect active landslides from ground motion using hotspot analysis, and (iii) the distribution characteristics of the detected landslides are investigated by examining their relationships with topographic and hydrological factors. Three expressways in Sichuan Province, China—namely the Yakang (Ya’an-Kangding), Yaxi (Ya’an-Xichang), and Lushi (Luding-Shimian) expressways—and their surrounding regions (a total area of approximately 20,000 square kilometers) were chosen as the study area. A total of 413 landslides were detected, among which 320 were detected using multi-temporal satellite optical images, and 109 were detected using GACOS-assisted InSAR stacking. It should be noted that only 16 landslides were detected by both approaches; these landslides all exhibited not only obvious geomorphological features but also ground motion. A statistical analysis of the topographic and hydrological factors shows that of the detected landslides: 81% are distributed at elevations of 1000–2500 m, over 60% lie within the elevation range of 100~400 m, and 90% present with medium and steep slopes (20°~45°), and 80% are located within areas seeing an annual rainfall of 950~1050 mm. Nine landslides were found to pose potential safety hazards to the expressways. The research findings in this paper have directly benefitted the Sichuan expressways; equally important, it is believed that the technical framework presented in this paper will provide guidance for hazard mitigation and the prevention of transportation hazards in the future.

Machine learning powered high-resolution co-seismic landslide detection

Numerous co-seismic landslides can be triggered by a strong earthquake. Fast and accurate detection and mapping of these landslides are crucial for rapid risk assessment and humanitarian assistance. Traditional visual interpretation is time-consuming and heavily influenced by human judgement. This paper presents an integrated machine learning (ML) powered method for co-seismic landslide detection, which combines multi-source data, pixel-based and object-based treatments, and ML techniques. The proposed method first fuses multi-source data, including optical images, synthetic aperture radar images and digital elevation models, to produce data layers and reference landslide inventories for learning. After that, ML algorithms are coupled with pixel-based and object-based treatments to produce a series of co-seismic landslide detection models. Powerful models are subsequently recommended after comprehensive evaluation. Two case studies of earthquakes in China are presented. The first is in the epicenter area of the 2008 Wenchuan earthquake. Even trained with only 5% of local data, the proposed method still achieves an accuracy of area (AOA) of 97.77% in the trained area and an AOA of 93.17% in a new area. If trained with the entire local data, an AOA of 99.99% in the trained area and 94.56% in a new area can be obtained. The second case detects the co-seismic landslides induced by the 2017 Jiuzhaigou earthquake. An AOA of 96.55% is achieved with 5% of local data. The case studies confirm the outstanding performance and generic nature of the proposed machine learning method, greatly advancing the state of the art of high-resolution co-seismic landslide detection and the landslide science.

Texture Feature Extraction and Morphological Analysis of Landslide Based on Image Edge Detection

Landslides in nature are harmful to economic development and people’s lives and cause irreparable losses to the environment. With the application of image detection technology and intelligent algorithm, a new way for landslide detection is proposed to achieve effective detection and identification of hazards. This paper takes the landslide as the data set, carries on the noise reduction, the image expansion, and the image segmentation processing to the image, and extracts the object region information. The quantitative description of the azimuth displacement and displacement change of the crack curve is completed in this paper. This method is suitable for 3D simulation model, sand and stone model, soil model, and the sliding test results of Panzhihua Flight Field, which proves that the design method is effective. Experiments show that when sliding occurs, the texture and color become chaotic, the usual mountain becomes more in the regular state, and the extraction of features is very different. The method has better recognition effect for the hillside covered with vegetation, the recognition time is short, and the recognition rate can reach 90%.

A novel energy efficient routing scheme for wireless sensor networks

In the current rapid developing and smart world, the wireless sensor networks domain is among the most emergent fields with plenty of applications such as healthcare, wildlife, environmental monitoring, defense, and landslide detection. Distribution of cluster heads along with the selection of cluster heads is essentially vital for optimizing various network performance parameters. In this paper, a novel energy efficient routing scheme based on probabilistic sector wise clustering has been proposed, which results in energy saving in conjunction with superior network lifetime for wireless sensor networks. In the proposed routing technique, the sensing field is divided into multiple sectors and clusters in five different types. Nodes in the sector can communicate directly with the base station in one-hop or through the gateway node in two-hops. Nodes in the cluster communicate to the base station through the cluster head in three-hops. The simulation results of all five types are compared in terms of their life span. Life span of the network is analyzed by considering the round number in which the first node dies, the round number till which 80% of the nodes are alive, 50% of nodes are alive and 20% of the nodes are alive.

A Study on Landslide Detection Methods for Reducing Casualties

Abstract: Landslides are one of the major disasters that frequently happen every year. Due to its occurrence,massive loss of lives arises. Recently Kerala was affected by this endangered disaster which happened at the hill tops of Kottayam district in Kerala. Landslides are nothing but the movement of mass of rock,debris down a slope. Mostly landslides are due to natural and man-made activities. We are available with different methodsto tackle this situation. Landslide early warning systems are one of the best ways to save individuals’ lives. This work deals with different methods to detect landslides such as IoT based alerting system, predictions using machine learning and deep learning, with the help of ZigBee networks and using fuzzy logic methods etc . This way we can detect whether there is a chance for a landslide occurrence.

Correction to: Landslide detection from bitemporal satellite imagery using attention‑based deep neural networks

Correction to: Landslide detection from bitemporal satellite imagery using attention‑based deep neural networks

Machine learning and landslide studies: recent advances and applications

Upon the introduction of machine learning (ML) and its variants, in the form that we know today, to the landslide community, many studies have been carried out to explore the usefulness of ML in landslide research and to look at some classic landslide problems from an ML point of view. ML techniques, including deep learning methods, are becoming popular to model complex landslide problems and are starting to demonstrate promising predictive performance compared to conventional methods. Almost all the studies published in the literature in recent years belong to one of the following three broad categories: landslide detection and mapping, landslide spatial forecasting in the form of susceptibility mapping, and landslide temporal forecasting. In this paper, we present a brief overview of ML techniques, provide a general summary of the landslide studies conducted, in recent years, in the three above-mentioned categories, and make an attempt to critically evaluate the use of ML methods to model landslide processes. The paper also provides suggestions for future use of these powerful data-driven techniques in landslide studies.

Landslide detection from bitemporal satellite imagery using attention-based deep neural networks

Landslide detection from bitemporal satellite imagery using attention-based deep neural networks

Automatic Detection of Coseismic Landslides Using a New Transformer Method

Earthquake-triggered landslides frequently occur in active mountain areas, which poses great threats to the safety of human lives and public infrastructures. Fast and accurate mapping of coseismic landslides is important for earthquake disaster emergency rescue and landslide risk analysis. Machine learning methods provide automatic solutions for landslide detection, which are more efficient than manual landslide mapping. Deep learning technologies are attracting increasing interest in automatic landslide detection. CNN is one of the most widely used deep learning frameworks for landslide detection. However, in practice, the performance of the existing CNN-based landslide detection models is still far from practical application. Recently, Transformer has achieved better performance in many computer vision tasks, which provides a great opportunity for improving the accuracy of landslide detection. To fill this gap, we explore whether Transformer can outperform CNNs in the landslide detection task. Specifically, we build a new dataset for identifying coseismic landslides. The Transformer-based semantic segmentation model SegFormer is employed to identify coseismic landslides. SegFormer leverages Transformer to obtain a large receptive field, which is much larger than CNN. SegFormer introduces overlapped patch embedding to capture the interaction of adjacent image patches. SegFormer also introduces a simple MLP decoder and sequence reduction to improve its efficiency. The semantic segmentation results of SegFormer are further improved by leveraging image processing operations to distinguish different landslide instances and remove invalid holes. Extensive experiments have been conducted to compare Transformer-based model SegFormer with other popular CNN-based models, including HRNet, DeepLabV3, Attention-UNet, U2Net and FastSCNN. SegFormer improves the accuracy, mIoU, IoU and F1 score of landslide detectuin by 2.2%, 5% and 3%, respectively. SegFormer also reduces the pixel-wise classification error rate by 14%. Both quantitative evaluation and visualization results show that Transformer is capable of outperforming CNNs in landslide detection.

Landslide Detection Based on ResU-Net with Transformer and CBAM Embedded: Two Examples with Geologically Different Environments

An efficient method of landslide detection can provide basic scientific data for emergency command and landslide susceptibility mapping. Compared to a traditional landslide detection approach, convolutional neural networks (CNN) have been proven to have powerful capabilities in reducing the time consumed for selecting the appropriate features for landslides. Currently, the success of transformers in natural language processing (NLP) demonstrates the strength of self-attention in global semantic information acquisition. How to effectively integrate transformers into CNN, alleviate the limitation of the receptive field, and improve the model generation are hot topics in remote sensing image processing based on deep learning (DL). Inspired by the vision transformer (ViT), this paper first attempts to integrate a transformer into ResU-Net for landslide detection tasks with small datasets, aiming to enhance the network ability in modelling the global context of feature maps and drive the model to recognize landslides with a small dataset. Besides, a spatial and channel attention module was introduced into the decoder to effectually suppress the noise in the feature maps from the convolution and transformer. By selecting two landslide datasets with different geological characteristics, the feasibility of the proposed model was validated. Finally, the standard ResU-Net was chosen as the benchmark to evaluate the proposed model rationality. The results indicated that the proposed model obtained the highest mIoU and F1-score in both datasets, demonstrating that the ResU-Net with a transformer embedded can be used as a robust landslide detection method and thus realize the generation of accurate regional landslide inventory and emergency rescue.

Landslide Inventory in the Downstream of the Niulanjiang River with ALOS PALSAR and Sentinel-1 Datasets

Landslide inventory and deformation monitoring is an essential task for human life and property security during the exploitation process of hydroelectric power resources. Synthetic Aperture Radar Interferometry (InSAR) is recognized as an effective tool for ground displacement monitoring with the advantages of wide coverage and high accuracy. In this study, we mapped the unstable slopes in the downstream of the Niulanjiang River with 22 ALOS PALSAR SAR images acquired from 2007 to 2011, and 90 Sentinel-1 SAR images from 2015 to 2019. A total of 94 active slopes are identified using a displacement map from the two datasets based on Small BAseline Subset (SBAS) InSAR analysis. By comparing the results from ALOS PALSAR and Sentinel-1 data stacks, we find that the number of active slopes increased dramatically. Several impact factors, e.g., earthquake, concentrated rainfall, and construction of hydropower stations, are discussed through time series analysis of typical landslides. Furthermore, nonlinear displacement of natural unstable slopes are found to be correlated with rainfall. A climate-driven model is used to qualify the relationship between rainfall and landslide displacement. Our results can provide valuable information for landslide detection and prevention.

Efficient Detection of Earthquake−Triggered Landslides Based on U−Net++: An Example of the 2018 Hokkaido Eastern Iburi (Japan) Mw = 6.6 Earthquake

Efficient detection of earthquake−triggered landslides is crucial for emergency response and risk assessment. With the development of multi−source remote sensing images, artificial intelligence has gradually become a powerful landslide detection method for similar tasks, aiming to mitigate time−consuming problems and meet emergency requirements. In this study, a relatively new deep learning (DL) network, called U−Net++, was designed to detect landslides for regions affected by the Iburi, Japan Mw = 6.6 earthquake, with only small training samples. For feature extraction, ResNet50 was selected as the feature extraction layer, and transfer learning was adopted to introduce the pre−trained weights for accelerating the model convergence. To prove the feasibility and validity of the proposed model, the random forest algorithm (RF) was selected as the benchmark, and the F1−score, Kappa coefficient, and IoU (Intersection of Union) were chosen to quantitatively evaluate the model’s performance. In addition, the proposed model was trained with different sample sizes (256,512) and network depths (3,4,5), respectively, to analyze their impacts on performance. The results showed that both models detected the majority of landslides, while the proposed model obtained the highest metric value (F1−score = 0.7580, Kappa = 0.7441, and IoU = 0.6104) and was capable of resisting the noise. In addition, the proposed model trained with sample size 256 possessed optimal performance, proving that the size is a non−negligible parameter in U−Net++, and it was found that the U−Net++ trained with shallower layer 3 yielded better results than that with the standard layer 5. Finally, the outstanding performance of the proposed model on a public landslide dataset demonstrated the generalization of U−Net++.

Quantitative Land-Use and Landslide Assessment: A Case Study in Rize, Türkiye

Currently, many studies have reported that many landslides occur in tea or rubber plantation areas. In these areas, it is important to make a landslide susceptibility map and to take necessary measures to mitigate landslide damage. However, since historical landslide distribution data and land use data are not available, quantitative landslide assessment measurements have not been made in many countries. Therefore, in this study, landslide distribution maps and land use maps are created with worldwide available satellite imagery and Google Earth imagery, and the relationship between landslides and land use is analyzed in Rize, Türkiye. The results show that landslides are 1.75 to 5 times more likely to occur in tea gardens than in forests. It was also found that land use has the highest contribution to landslides among the landslide conditioning factors. The landslide assessment, using a simple landslide detection method and land use classification method with worldwide available data, enabled us to quantitatively reveal the characteristics of landslides. The results of this study reveal that quantitative landslide assessments can be applied in any location, where relatively high resolution satellite imagery and Google Earth imagery, or its alternatives, are available.

A New Deep Learning Neural Network Model for the Identification of InSAR Anomalous Deformation Areas

The identification and early warning of potential landslides can effectively reduce the number of casualties and the amount of property loss. At present, interferometric synthetic aperture radar (InSAR) is considered one of the mainstream methods for the large-scale identification and detection of potential landslides, and it can obtain long-term time-series surface deformation data. However, the method of identifying anomalous deformation areas using InSAR data is still mainly manual delineation, which is time-consuming, labor-consuming, and has no generally accepted criterion. In this study, a two-stage detection deep learning network (InSARNet) is proposed and used to detect anomalous deformation areas in Maoxian County, Sichuan Province. Compared with the most commonly used detection models, it is demonstrated that the InSARNet has a better performance in the detection of anomalous deformation in mountainous areas, and all of the quantitative evaluation indexes are higher for InSARNet than for the other models. After the anomalous deformation areas are identified using the proposed model, the possible relationship between the anomalous deformation areas and potential landslides is investigated. Finally, the fact that the automatic and rapid identification of potential landslides is the inevitable trend of future development is discussed.

IoT based Landslide Detection and Monitoring System

Abstract: According to recent survey 64.15% of fatalities are due to natural calamities which includes landslide as the major problem. Studies show that due time consuming and unreliable prediction system there is increase in rate of fatalities due to landslide. Only way to reduce these severe effects is predicting landslide efficiently and accurately without consuming much time. Most of the papers surveyed use sensor technology, and the most commonly used one is WSN (Wireless Sensor Network) since this sensor network provides large scale monitoring. If the chance of occurrence of landslide is high after the prediction an alert is sent to the disaster management department. Each of these methods have different percentage of accuracy. This survey paper discusses various approaches for detecting and predicting landslide thereby reducing fatalities. Keywords: Gyro sensor, Soil sensor, NodeMCU, Aurdino IDE, Blynk.