The Potential of Remote Sensing to Assess Conditioning Factors for Landslide Detection at a Regional Scale: The Case in Southeastern Colombia

2020 ◽  
Author(s):  
Nixon Alexander Correa-Muñoz ◽  
Carol Andrea Murillo-Feo
Keyword(s):  
Remote Sensing ◽  
Regional Scale ◽  
Training Data ◽  
Sar Interferometry ◽  
Optical Remote Sensing ◽  
High Association ◽  
Conditioning Factors ◽  
Explanatory Variables ◽  
Detection Model ◽  
Remote Sensing Techniques

This landslide detection research applied remote sensing techniques. Morphometry to derive both DEM terrain parameters and land use variables. SAR interferometry (InSAR) for showing that InSAR coherence and InSAR displacement obtained with SRTM DEM 30 m resolution were strongly related to landslides. InSAR coherence values from 0.43 to 0.66 had a high association with landslides. PS-InSAR allowed to estimate terrain velocities in the satellite line-of-sight (LOS) in the range − 10 to 10 mm/year concerning extremely slow landslide displacement rates. SAR polarimetry (PolSAR) was used over L-band UAVSAR quad-pol data, obtaining the scattering mechanism of volume and surface retrodispersion more associated with landslides. The optical remote sensing with a multitemporal approach for change detection by multi-year Landsat (5, 7 and 8)-NDVI, showed that NDVI related to landslides had values between 0.42 and 0.72. All the information was combined into a multidimensional grid product and crossed with training data containing a Colombian Geologic Service (CGS) landslide inventory. A detection model was implemented using the Random Forest supervised method relating the training sample of landslides with multidimensional explanatory variables. A test sample with a proportion of 70:30 allowed to find the accuracy of detection of about 70.8% for slides type.

Design of global-contextual detection model for optical remote sensing targets

2020 ◽  
Vol 13 (6) ◽  
pp. 1-12
Author(s):  
ZHANG Rui-yan ◽  
◽  
JIANG Xiu-jie ◽  
AN Jun-she ◽  
CUI Tian-shu ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Optical Remote Sensing ◽  
Detection Model

Optimal Detection and Estimation of Marine Oil Spills Through Coherent Pluralism

2013 ◽  
Vol 4 (1) ◽  
pp. 84-111
Author(s):  
Kufre Bassey ◽  
Polycarp Chigbu
Keyword(s):  
Remote Sensing ◽  
Environmental Science ◽  
Oil Spills ◽  
False Alarms ◽  
Optical Remote Sensing ◽  
Marine Oil ◽  
Detection And Estimation ◽  
Number Of False Alarms ◽  
Marine Oil Spills ◽  
Remote Sensing Techniques

An important area of environmental science involves the combination of information from diverse sources relating to a similar endpoint. Majority of optical remote sensing techniques used for marine oil spills detection have been reported lately of having high number of false alarms (oil slick look-a-likes) phenomena which give rise to signals which appear to be oil but are not. Suggestions for radar image as an operational tool has also been made. However, due to the inherent risk in these tools, this paper presents the possible research directions of combining statistical techniques with remote sensing in marine oil spill detection and estimation.

scholarly journals Estimation of Winter Wheat Residue Coverage Using Optical and SAR Remote Sensing Images

2019 ◽  
Vol 11 (10) ◽  
pp. 1163
Author(s):  
Wenting Cai ◽  
Shuhe Zhao ◽  
Yamei Wang ◽  
Fanchen Peng ◽  
Joon Heo ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Crop Residues ◽  
Regional Scale ◽  
Microwave Remote Sensing ◽  
Estimation Accuracy ◽  
Coefficient Of Determination ◽  
Accurate Estimation ◽  
Optical Remote Sensing ◽  
Optimal Subset ◽  
Subset Regression

As an important part of the farmland ecosystem, crop residues provide a barrier against water erosion, and improve soil quality. Timely and accurate estimation of crop residue coverage (CRC) on a regional scale is essential for understanding the condition of ecosystems and the interactions with the surrounding environment. Satellite remote sensing is an effective way of regional CRC estimation. Both optical remote sensing and microwave remote sensing are common means of CRC estimation. However, CRC estimation based on optical imagery has the shortcomings of signal saturation in high coverage areas and susceptibility to weather conditions, while CRC estimation using microwave imagery is easily influenced by soil moisture and crop types. Synergistic use of optical and microwave remote sensing information may have the potential to improve estimation accuracy. Therefore, the objectives of this study were to: (i) Analyze the correlation between field measured CRC and satellite derived variables based on Sentinel-1 and Sentinel-2, (ii) investigate the relationship of CRC with new indices (OCRI-RPs) which combine optical crop residues indices (OCRIs) and radar parameters (RPs), and (iii) to estimate CRC in Yucheng County based on OCRI-RPs by optimal subset regression. The correlations between field measured CRC and satellite derived variables were evaluated by coefficient of determination (R2) and root mean square error (RMSE). The results showed that the normalized difference tillage index (NDTI) and radar indices 2 (RI2) had relatively higher correlations with field measured CRC in OCRIs and RPs (R2 = 0.570, RMSE = 6.560% and R2 = 0.430, RMSE = 7.052%, respectively). Combining OCRIs with RPs by multiplying each OCRI with each RP could significantly improve the ability of indices to estimate CRC, as NDTI × RI2 had the highest R2 value of 0.738 and lowest RMSE value of 5.140%. The optimal model for CRC estimation by optimal subset regression was constructed by NDI71 × σ V V 0 and NDTI × σ V H 0 , with a R2 value of 0.770 and a RMSE value of 4.846%, which had a great improvement when compared with the best results in OCRIs and RPs. The results demonstrated that the combination of optical remote sensing information and microwave remote sensing information could improve the accuracy of CRC estimation.

scholarly journals Flash-Flood Susceptibility Assessment Using Multi-Criteria Decision Making and Machine Learning Supported by Remote Sensing and GIS Techniques

2019 ◽  
Vol 12 (1) ◽  
pp. 106 ◽  
Author(s):  
Romulus Costache ◽  
Quoc Bao Pham ◽  
Ehsan Sharifi ◽  
Nguyen Thi Thuy Linh ◽  
S.I. Abba ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Information Gain ◽  
Flash Flood ◽  
Slope Angle ◽  
Training Data ◽  
Operating Characteristics ◽  
Predictive Capability ◽  
Data Set ◽  
Flood Susceptibility ◽  
Remote Sensing Techniques

Concerning the significant increase in the negative effects of flash-floods worldwide, the main goal of this research is to evaluate the power of the Analytical Hierarchy Process (AHP), fi (kNN), K-Star (KS) algorithms and their ensembles in flash-flood susceptibility mapping. To train the two stand-alone models and their ensembles, for the first stage, the areas affected in the past by torrential phenomena are identified using remote sensing techniques. Approximately 70% of these areas are used as a training data set along with 10 flash-flood predictors. It should be remarked that the remote sensing techniques play a crucial role in obtaining eight out of 10 flash-flood conditioning factors. The predictive capability of predictors is evaluated through the Information Gain Ratio (IGR) method. As expected, the slope angle results in the factor with the highest predictive capability. The application of the AHP model implies the construction of ten pair-wise comparison matrices for calculating the normalized weights of each flash-flood predictor. The computed weights are used as input data in kNN–AHP and KS–AHP ensemble models for calculating the Flash-Flood Potential Index (FFPI). The FFPI also is determined through kNN and KS stand-alone models. The performance of the models is evaluated using statistical metrics (i.e., sensitivity, specificity and accuracy) while the validation of the results is done by constructing the Receiver Operating Characteristics (ROC) Curve and Area Under Curve (AUC) values and by calculating the density of torrential pixels within FFPI classes. Overall, the best performance is obtained by the kNN–AHP ensemble model.

Estimating Biomass for New Zealand Pasture Using Optical Remote Sensing Techniques

1999 ◽  
Vol 14 (3) ◽  
pp. 89-94 ◽  
Author(s):  
M. M. Hanna ◽  
D. A. Steyn-Ross ◽  
Moira Steyn-Ross
Keyword(s):  
Remote Sensing ◽  
New Zealand ◽  
Optical Remote Sensing ◽  
Remote Sensing Techniques

scholarly journals Individual Tree-Crown Detection in RGB Imagery Using Semi-Supervised Deep Learning Neural Networks

2019 ◽  
Vol 11 (11) ◽  
pp. 1309 ◽  
Author(s):  
Ben G. Weinstein ◽  
Sergio Marconi ◽  
Stephanie Bohlman ◽  
Alina Zare ◽  
Ethan White
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Training Data ◽  
Tree Crown ◽  
Individual Tree ◽  
Detection Model ◽  
High Resolution Imagery ◽  
The Neural Network ◽  
Detection Approach ◽  
Crown Delineation

Remote sensing can transform the speed, scale, and cost of biodiversity and forestry surveys. Data acquisition currently outpaces the ability to identify individual organisms in high resolution imagery. We outline an approach for identifying tree-crowns in RGB imagery while using a semi-supervised deep learning detection network. Individual crown delineation has been a long-standing challenge in remote sensing and available algorithms produce mixed results. We show that deep learning models can leverage existing Light Detection and Ranging (LIDAR)-based unsupervised delineation to generate trees that are used for training an initial RGB crown detection model. Despite limitations in the original unsupervised detection approach, this noisy training data may contain information from which the neural network can learn initial tree features. We then refine the initial model using a small number of higher-quality hand-annotated RGB images. We validate our proposed approach while using an open-canopy site in the National Ecological Observation Network. Our results show that a model using 434,551 self-generated trees with the addition of 2848 hand-annotated trees yields accurate predictions in natural landscapes. Using an intersection-over-union threshold of 0.5, the full model had an average tree crown recall of 0.69, with a precision of 0.61 for the visually-annotated data. The model had an average tree detection rate of 0.82 for the field collected stems. The addition of a small number of hand-annotated trees improved the performance over the initial self-supervised model. This semi-supervised deep learning approach demonstrates that remote sensing can overcome a lack of labeled training data by generating noisy data for initial training using unsupervised methods and retraining the resulting models with high quality labeled data.

Sign in / Sign up

Export Citation Format

Share Document