scholarly journals Evaluation of the Effectiveness of Multiple Machine Learning Methods in Remote Sensing Quantitative Retrieval of Suspended Matter Concentrations: A Case Study of Nansi Lake in North China

2021 ◽  
Vol 2021 ◽  
pp. 1-17
Author(s):  
Xiuyu Liu ◽  
Zhen Zhang ◽  
Tao Jiang ◽  
Xuehua Li ◽  
Yanyi Li
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Random Forest ◽  
Suspended Matter ◽  
North China ◽  
Ocean Color ◽  
Remote Sensing Data ◽  
Quality Parameters ◽  
Nansi Lake ◽  
Important Indicator

Total suspended matter (TSM) is a core parameter in the quantitative retrieval of ocean color remote sensing and an important indicator for evaluating the quality of the aquatic environment. This study selects part of Nansi Lake in North China as the study area. Researchers used Hyperion remote sensing data and field-measured TSM concentration as data sources. Firstly, the characteristic variables with high correlation were selected based on spectral analysis. Then, seven methods such as linear regression, BP neural network (BP), KNN, random forest (RF), and random forest based on genetic algorithm optimization (GA_RF) are used to construct the inversion model of TSM concentration. The retrieval accuracy of each model shows that the machine learning models are much more accurate than the linear model. Among them, the GA_RF model retrieves the suspended solids concentration with the best performance and the highest prediction accuracy, with a determination coefficient R2 of 0.98, a root mean square error (RMSE) of 1.715 mg/L, and an average relative error (ARE) of 6.83%. Additionally, the spatial distribution of TSM concentration was inversed by Hyperion remote sensing image. The results showed that the concentration of TSM was lower in the northwest and higher in the southeast, and the concentration distribution was uneven, showing the characteristics of a typical shallow macrophytic lake. This study provides an effective method for monitoring TSM concentration and other water quality parameters in the shallow macrophytic lake and further proves the advantages of machine learning in ocean color inversion. All in all, this research provides some useful methods and suggestions for quantitative inversion of TSM concentration in shallow macrophytic lakes.

scholarly journals Comparison of Machine Learning Algorithms for Wildland-Urban Interface Fuelbreak Planning Integrating ALS and UAV-Borne LiDAR Data and Multispectral Images

Drones ◽  
2020 ◽  
Vol 4 (2) ◽  
pp. 21 ◽  
Author(s):  
Francisco Rodríguez-Puerta ◽  
Rafael Alonso Ponce ◽  
Fernando Pérez-Rodríguez ◽  
Beatriz Águeda ◽  
Saray Martín-García ◽  
...  
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Random Forest ◽  
Learning Algorithms ◽  
Remote Sensing Data ◽  
Machine Learning Algorithms ◽  
Data Sources ◽  
Lidar Data ◽  
Sensing Data ◽  
Sentinel 2

Controlling vegetation fuels around human settlements is a crucial strategy for reducing fire severity in forests, buildings and infrastructure, as well as protecting human lives. Each country has its own regulations in this respect, but they all have in common that by reducing fuel load, we in turn reduce the intensity and severity of the fire. The use of Unmanned Aerial Vehicles (UAV)-acquired data combined with other passive and active remote sensing data has the greatest performance to planning Wildland-Urban Interface (WUI) fuelbreak through machine learning algorithms. Nine remote sensing data sources (active and passive) and four supervised classification algorithms (Random Forest, Linear and Radial Support Vector Machine and Artificial Neural Networks) were tested to classify five fuel-area types. We used very high-density Light Detection and Ranging (LiDAR) data acquired by UAV (154 returns·m−2 and ortho-mosaic of 5-cm pixel), multispectral data from the satellites Pleiades-1B and Sentinel-2, and low-density LiDAR data acquired by Airborne Laser Scanning (ALS) (0.5 returns·m−2, ortho-mosaic of 25 cm pixels). Through the Variable Selection Using Random Forest (VSURF) procedure, a pre-selection of final variables was carried out to train the model. The four algorithms were compared, and it was concluded that the differences among them in overall accuracy (OA) on training datasets were negligible. Although the highest accuracy in the training step was obtained in SVML (OA=94.46%) and in testing in ANN (OA=91.91%), Random Forest was considered to be the most reliable algorithm, since it produced more consistent predictions due to the smaller differences between training and testing performance. Using a combination of Sentinel-2 and the two LiDAR data (UAV and ALS), Random Forest obtained an OA of 90.66% in training and of 91.80% in testing datasets. The differences in accuracy between the data sources used are much greater than between algorithms. LiDAR growth metrics calculated using point clouds in different dates and multispectral information from different seasons of the year are the most important variables in the classification. Our results support the essential role of UAVs in fuelbreak planning and management and thus, in the prevention of forest fires.

scholarly journals Large-Scale Crop Mapping Based on Machine Learning and Parallel Computation with Grids

2019 ◽  
Vol 11 (12) ◽  
pp. 1500 ◽  
Author(s):  
Ning Yang ◽  
Diyou Liu ◽  
Quanlong Feng ◽  
Quan Xiong ◽  
Lin Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Time Series ◽  
Parallel Computing ◽  
Random Forest ◽  
Large Scale ◽  
Remote Sensing Data ◽  
Remote Sensing Images ◽  
Medium Resolution ◽  
Crop Mapping

Large-scale crop mapping provides important information in agricultural applications. However, it is a challenging task due to the inconsistent availability of remote sensing data caused by the irregular time series and limited coverage of the images, together with the low spatial resolution of the classification results. In this study, we proposed a new efficient method based on grids to address the inconsistent availability of the high-medium resolution images for large-scale crop classification. First, we proposed a method to block the remote sensing data into grids to solve the problem of temporal inconsistency. Then, a parallel computing technique was introduced to improve the calculation efficiency on the grid scale. Experiments were designed to evaluate the applicability of this method for different high-medium spatial resolution remote sensing images and different machine learning algorithms and to compare the results with the widely used nonparallel method. The computational experiments showed that the proposed method was successful at identifying large-scale crop distribution using common high-medium resolution remote sensing images (GF-1 WFV images and Sentinel-2) and common machine learning classifiers (the random forest algorithm and support vector machine). Finally, we mapped the croplands in Heilongjiang Province in 2015, 2016, 2017, which used a random forest classifier with the time series GF-1 WFV images spectral features, the enhanced vegetation index (EVI) and normalized difference water index (NDWI). Ultimately, the accuracy was assessed using a confusion matrix. The results showed that the classification accuracy reached 88%, 82%, and 85% in 2015, 2016, and 2017, respectively. In addition, with the help of parallel computing, the calculation speed was significantly improved by at least seven-fold. This indicates that using the grid framework to block the data for classification is feasible for crop mapping in large areas and has great application potential in the future.

scholarly journals Machine learning with remote sensing data to locate uncontacted indigenous villages in Amazonia

2018 ◽  
Author(s):  
Robert S Walker ◽  
Marcus J Hamilton
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Random Forest ◽  
Remote Sensing Data ◽  
Indigenous Populations ◽  
Machine Learning Techniques ◽  
Training Dataset ◽  
Small Scale ◽  
Sensing Data ◽  
External Threats

Background. The world’s last uncontacted indigenous societies in Amazonia have only intermittent and often hostile interactions with the outside world. Knowledge of their locations is essential for urgent protection efforts, but their extreme isolation, small populations, and semi-nomadic lifestyles make this a challenging task. Methods. Remote sensing technology with Landsat satellite sensors is a non-invasive methodology to track isolated indigenous populations through time. However, the small-scale nature of the deforestation signature left by uncontacted populations clearing villages and gardens has similarities to those made by contacted indigenous villages. Both contacted and uncontacted indigenous populations often live in proximity to one another making it difficult to distinguish the two in satellite imagery. Here we use machine learning techniques applied to remote sensing data with a training dataset of 500 contacted and 25 uncontacted villages. Results. Uncontacted villages generally have smaller cleared areas, reside at higher elevations, and are farther from populated places and satellite-detected lights at night. A random forest algorithm with an optimally-tuned detection cutoff has a leave-one-out cross-validated sensitivity and specificity of over 98%. A grid search around known uncontacted villages led us to identify 3 previously-unknown villages using predictions from the random forest model. Our efforts can improve policies toward isolated populations by providing better near real-time knowledge of their locations and movements in relation to encroaching loggers, settlers, and other external threats to their survival.

Retrieval of Water Quality Parameters in Lake Ontario Based on Hyperspectral Remote Sensing Data and Intelligent Algorithms

2020 ◽  
Author(s):  
Yu Li ◽  
Youyue Sun ◽  
Jinhui Jeanne Huang ◽  
Edward McBean
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Water Quality ◽  
Remote Sensing Data ◽  
Quality Parameters ◽  
Hyperspectral Remote Sensing ◽  
Optically Active ◽  
Water Quality Parameters ◽  
Support Vector ◽  
Sensing Data

<p>With the increasingly prominent ecological and environmental problems in lakes, the monitoring water quality in lakes by satellite remote sensing is becoming more and more high demanding. Traditional water quality sampling is normally conducted manually and are time-consuming and labor-costly. It could not provide a full picture of the waterbodies over time due to limited sampling points and low sampling frequency. A novel attempt is proposed to use hyperspectral remote sensing in conjunction with machine learning technologies to retrieve water quality parameters and provide mapping for these parameters in a lake. The retrieval of both optically active parameters: Chlorophyll-a (CHLA) and dissolved oxygen concentration (DO), as well as non-optically active parameters: total phosphorous (TP), total nitrogen (TN), turbidity (TB), pH were studied in this research. A comparison of three machine learning algorithms including Random Forests (RF), Support Vector Regression (SVR) and Artificial Neural Networks were conducted. These water parameters collected by the Environment and Climate Change Canada agency for 20 years were used as the ground truth for model training and validation. Two set of remote sensing data from MODIS and Sentinel-2 were utilized and evaluated. This research proposed a new approach to retrieve both optically active parameters and non-optically active parameters for water body and provide new strategy for water quality monitoring.</p>

scholarly journals Woody Aboveground Biomass Mapping of the Brazilian Savanna with a Multi-Sensor and Machine Learning Approach

2020 ◽  
Vol 12 (17) ◽  
pp. 2685 ◽  
Author(s):  
Polyanna da Conceição Bispo ◽  
Pedro Rodríguez-Veiga ◽  
Barbara Zimbres ◽  
Sabrina do Couto de Miranda ◽  
Cassio Henrique Giusti Cezare ◽  
...  
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Random Forest ◽  
Aboveground Biomass ◽  
Large Scale ◽  
Remote Sensing Data ◽  
Spatial And Temporal Variability ◽  
Landsat 8 ◽  
Learning Approach ◽  
Machine Learning Approach

The tropical savanna in Brazil known as the Cerrado covers circa 23% of the Brazilian territory, but only 3% of this area is protected. High rates of deforestation and degradation in the woodland and forest areas have made the Cerrado the second-largest source of carbon emissions in Brazil. However, data on these emissions are highly uncertain because of the spatial and temporal variability of the aboveground biomass (AGB) in this biome. Remote-sensing data combined with local vegetation inventories provide the means to quantify the AGB at large scales. Here, we quantify the spatial distribution of woody AGB in the Rio Vermelho watershed, located in the centre of the Cerrado, at a high spatial resolution of 30 metres, with a random forest (RF) machine-learning approach. We produced the first high-resolution map of the AGB for a region in the Brazilian Cerrado using a combination of vegetation inventory plots, airborne light detection and ranging (LiDAR) data, and multispectral and radar satellite images (Landsat 8 and ALOS-2/PALSAR-2). A combination of random forest (RF) models and jackknife analyses enabled us to select the best remote-sensing variables to quantify the AGB on a large scale. Overall, the relationship between the ground data from vegetation inventories and remote-sensing variables was strong (R2 = 0.89), with a root-mean-square error (RMSE) of 7.58 Mg ha−1 and a bias of 0.43 Mg ha−1.

scholarly journals Machine learning with remote sensing data to locate uncontacted indigenous villages in Amazonia

2018 ◽  
Author(s):  
Robert S Walker ◽  
Marcus J Hamilton
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Random Forest ◽  
Remote Sensing Data ◽  
Indigenous Populations ◽  
Machine Learning Techniques ◽  
Training Dataset ◽  
Small Scale ◽  
Sensing Data ◽  
External Threats

Background. The world’s last uncontacted indigenous societies in Amazonia have only intermittent and often hostile interactions with the outside world. Knowledge of their locations is essential for urgent protection efforts, but their extreme isolation, small populations, and semi-nomadic lifestyles make this a challenging task. Methods. Remote sensing technology with Landsat satellite sensors is a non-invasive methodology to track isolated indigenous populations through time. However, the small-scale nature of the deforestation signature left by uncontacted populations clearing villages and gardens has similarities to those made by contacted indigenous villages. Both contacted and uncontacted indigenous populations often live in proximity to one another making it difficult to distinguish the two in satellite imagery. Here we use machine learning techniques applied to remote sensing data with a training dataset of 500 contacted and 25 uncontacted villages. Results. Uncontacted villages generally have smaller cleared areas, reside at higher elevations, and are farther from populated places and satellite-detected lights at night. A random forest algorithm with an optimally-tuned detection cutoff has a leave-one-out cross-validated sensitivity and specificity of over 98%. A grid search around known uncontacted villages led us to identify 3 previously-unknown villages using predictions from the random forest model. Our efforts can improve policies toward isolated populations by providing better near real-time knowledge of their locations and movements in relation to encroaching loggers, settlers, and other external threats to their survival.

scholarly journals Identification of Poverty Areas by Remote Sensing and Machine Learning: A Case Study in Guizhou, Southwest China

2020 ◽  
Vol 10 (1) ◽  
pp. 11
Author(s):  
Jian Yin ◽  
Yuanhong Qiu ◽  
Bin Zhang
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Developing Countries ◽  
Random Forest ◽  
Poverty Reduction ◽  
Remote Sensing Data ◽  
Guizhou Province ◽  
Support Vector ◽  
Human Society ◽  
Nighttime Lights

As an objective social phenomenon, poverty has accompanied the vicissitudes of human society, which is a chronic dilemma hindering human civilization. Remote sensing data, such as nighttime lights imagery, provides abundant poverty-related information that can be related to poverty. However, it may be insufficient to rely merely on nighttime lights data, because poverty is a comprehensive problem, and poverty identification may be affected by topography, especially in some developing countries or regions where agriculture accounts for a large proportion. Therefore, some geographical features may be necessary for supplements. With the support of the random forest machine learning method, we extracted 23 spatial features base on remote sensing including nighttime lights data and geographical data, and carried out the poverty identification in Guizhou Province, China, since 2012. Compared with the identifications using support vector machines and the artificial neural network, random forest showed a better accuracy. The results supported that nighttime lights and geographical features are better than those only by nighttime lights features. From 2012 to 2019, the identified poor counties in Guizhou Province showed obvious dynamic spatiotemporal characteristics. The number of poor counties has decreased consistently and contiguous poverty-stricken areas have fragmented; the number of poor counties in the northeast and southwest regions decreased faster than other areas. The reduction in poverty probability exhibited a pattern of spreading from the central and northern regions to the periphery parts. The poverty reduction was relatively slow in areas with large slope and large topographic relief. When poor counties are adjacent to more non-poor counties, they can get rid of poverty easier. This study provides a method for feature selection and recognition of poor counties by remote sensing images and offers new insights into poverty identification and regional sustainable development for other developing countries and areas.

scholarly journals Machine learning with remote sensing data to locate uncontacted indigenous villages in Amazonia

2019 ◽  
Vol 5 ◽  
pp. e170 ◽  
Author(s):  
Robert S. Walker ◽  
Marcus J. Hamilton
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Random Forest ◽  
Remote Sensing Data ◽  
Indigenous Populations ◽  
Machine Learning Techniques ◽  
Training Dataset ◽  
Small Scale ◽  
Sensing Data ◽  
External Threats

Background The world’s last uncontacted indigenous societies in Amazonia have only intermittent and often hostile interactions with the outside world. Knowledge of their locations is essential for urgent protection efforts, but their extreme isolation, small populations, and semi-nomadic lifestyles make this a challenging task. Methods Remote sensing technology with Landsat satellite sensors is a non-invasive methodology to track isolated indigenous populations through time. However, the small-scale nature of the deforestation signature left by uncontacted populations clearing villages and gardens has similarities to those made by contacted indigenous villages. Both contacted and uncontacted indigenous populations often live in proximity to one another making it difficult to distinguish the two in satellite imagery. Here we use machine learning techniques applied to remote sensing data with a training dataset of 500 contacted and 25 uncontacted villages. Results Uncontacted villages generally have smaller cleared areas, reside at higher elevations, and are farther from populated places and satellite-detected lights at night. A random forest algorithm with an optimally-tuned detection cutoff has a leave-one-out cross-validated sensitivity and specificity of over 98%. A grid search around known uncontacted villages led us to identify three previously-unknown villages using predictions from the random forest model. Our efforts can improve policies toward isolated populations by providing better near real-time knowledge of their locations and movements in relation to encroaching loggers, settlers, and other external threats to their survival.

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.

Sign in / Sign up

Export Citation Format

Share Document