Classification Ensembles for Beach Cast and Drifting Vegetation Mapping with Sentinel-2 and PlanetScope

Along the Baltic coastline of Germany, drifting vegetation and beach cast create overlays at the otherwise sandy or stony beaches. These overlays influence the morphodynamics and structures of the beaches. To better understand the influence of these patchy habitats on coastal environments, regular monitoring is necessary. Most studies, however, have been conducted on spatially larger and temporally more stable occurrences of aquatic vegetation such as floating fields of Sargassum. Nevertheless, drifting vegetation and beach cast pose a particular challenge, as they exhibit high temporal dynamics and sometimes small spatial extent. Regular surveys and mappings are the traditional methods to record their habitats, but they are time-consuming and cost-intensive. Spaceborne remote sensing can provide frequent recordings of the coastal zone at lower cost. Our study therefore aims at the monitoring of drifting vegetation and beach cast on spatial scales between 3 and 10 m. We developed an automated coastline masking algorithm and tested six supervised classification methods and various classification ensembles for their suitability to detect small-scale assemblages of drifting vegetation and beach cast in a study area at the coastline of the Western Baltic Sea using multispectral data of the sensors Sentinel-2 MSI and PlanetScope. The shoreline masking algorithm shows high accuracies in masking the land area while preserving the sand-covered shoreline. We could achieve best classification results using PlanetScope data with an ensemble of a random forest classifier, cart classifier, support vector machine classifier, naïve bayes classifier and stochastic gradient boosting classifier. This ensemble accomplished a combined f1-score of 0.95. The accuracy of the Sentinel-2 classifications was lower but still achieved a combined f1-score of 0.86 for the same ensemble. The results of this study can be considered as a starting point for the development of time series analysis of the vegetation dynamics along Baltic beaches.

Download Full-text

Mapping of the Canopy Openings in Mixed Beech–Fir Forest at Sentinel-2 Subpixel Level Using UAV and Machine Learning Approach

Remote Sensing ◽

10.3390/rs12233925 ◽

2020 ◽

Vol 12 (23) ◽

pp. 3925

Author(s):

Ivan Pilaš ◽

Mateo Gašparović ◽

Alan Novkinić ◽

Damir Klobučar

Keyword(s):

Machine Learning ◽

Forest Canopy ◽

Vegetation Index ◽

Predictive Performance ◽

Spatial Extent ◽

Gradient Boosting ◽

Support Vector ◽

Stochastic Gradient Boosting ◽

Extreme Gradient Boosting ◽

Sentinel 2

The presented study demonstrates a bi-sensor approach suitable for rapid and precise up-to-date mapping of forest canopy gaps for the larger spatial extent. The approach makes use of Unmanned Aerial Vehicle (UAV) red, green and blue (RGB) images on smaller areas for highly precise forest canopy mask creation. Sentinel-2 was used as a scaling platform for transferring information from the UAV to a wider spatial extent. Various approaches to an improvement in the predictive performance were examined: (I) the highest R2 of the single satellite index was 0.57, (II) the highest R2 using multiple features obtained from the single-date, S-2 image was 0.624, and (III) the highest R2 on the multitemporal set of S-2 images was 0.697. Satellite indices such as Atmospherically Resistant Vegetation Index (ARVI), Infrared Percentage Vegetation Index (IPVI), Normalized Difference Index (NDI45), Pigment-Specific Simple Ratio Index (PSSRa), Modified Chlorophyll Absorption Ratio Index (MCARI), Color Index (CI), Redness Index (RI), and Normalized Difference Turbidity Index (NDTI) were the dominant predictors in most of the Machine Learning (ML) algorithms. The more complex ML algorithms such as the Support Vector Machines (SVM), Random Forest (RF), Stochastic Gradient Boosting (GBM), Extreme Gradient Boosting (XGBoost), and Catboost that provided the best performance on the training set exhibited weaker generalization capabilities. Therefore, a simpler and more robust Elastic Net (ENET) algorithm was chosen for the final map creation.

Download Full-text

Machine learning as a successful approach for predicting complex spatio–temporal patterns in animal species abundance

Animal Biodiversity and Conservation ◽

10.32800/abc.2021.44.0289 ◽

2021 ◽

pp. 289-301

Author(s):

B. Martín ◽

J. González–Arias ◽

J. A. Vicente–Vírseda

Keyword(s):

Machine Learning ◽

Random Forest ◽

Animal Species ◽

Temporal Patterns ◽

Additive Models ◽

Gradient Boosting ◽

Support Vector ◽

Stochastic Gradient Boosting ◽

Extreme Gradient Boosting ◽

Spatio Temporal

Our aim was to identify an optimal analytical approach for accurately predicting complex spatio–temporal patterns in animal species distribution. We compared the performance of eight modelling techniques (generalized additive models, regression trees, bagged CART, k–nearest neighbors, stochastic gradient boosting, support vector machines, neural network, and random forest –enhanced form of bootstrap. We also performed extreme gradient boosting –an enhanced form of radiant boosting– to predict spatial patterns in abundance of migrating Balearic shearwaters based on data gathered within eBird. Derived from open–source datasets, proxies of frontal systems and ocean productivity domains that have been previously used to characterize the oceanographic habitats of seabirds were quantified, and then used as predictors in the models. The random forest model showed the best performance according to the parameters assessed (RMSE value and R2). The correlation between observed and predicted abundance with this model was also considerably high. This study shows that the combination of machine learning techniques and massive data provided by open data sources is a useful approach for identifying the long–term spatial–temporal distribution of species at regional spatial scales.

Download Full-text

A Comparative Study of Different Machine Learning Algorithms in Predicting the Content of Ilmenite in Titanium Placer

Applied Sciences ◽

10.3390/app10020635 ◽

2020 ◽

Vol 10 (2) ◽

pp. 635 ◽

Cited By ~ 5

Author(s):

Yingli LV ◽

Qui-Thao Le ◽

Hoang-Bac Bui ◽

Xuan-Nam Bui ◽

Hoang Nguyen ◽

...

Keyword(s):

Soft Computing ◽

Mean Squared Error ◽

Machine Learning Algorithms ◽

Classification And Regression Tree ◽

Gradient Boosting ◽

Support Vector ◽

Stochastic Gradient Boosting ◽

Soft Computing Techniques ◽

Residuals Analysis ◽

Computing Models

In this study, the ilmenite content in beach placer sand was estimated using seven soft computing techniques, namely random forest (RF), artificial neural network (ANN), k-nearest neighbors (kNN), cubist, support vector machine (SVM), stochastic gradient boosting (SGB), and classification and regression tree (CART). The 405 beach placer borehole samples were collected from Southern Suoi Nhum deposit, Binh Thuan province, Vietnam, to test the feasibility of these soft computing techniques in estimating ilmenite content. Heavy mineral analysis indicated that valuable minerals in the placer sand are zircon, ilmenite, leucoxene, rutile, anatase, and monazite. In this study, five materials, namely rutile, anatase, leucoxene, zircon, and monazite, were used as the input variables to estimate ilmenite content based on the above mentioned soft computing models. Of the whole dataset, 325 samples were used to build the regarded soft computing models; 80 remaining samples were used for the models’ verification. Root-mean-squared error (RMSE), determination coefficient (R2), a simple ranking method, and residuals analysis technique were used as the statistical criteria for assessing the model performances. The numerical experiments revealed that soft computing techniques are capable of estimating the content of ilmenite with high accuracy. The residuals analysis also indicated that the SGB model was the most suitable for determining the ilmenite content in the context of this research.

Download Full-text

Predicting 90-Day and 1-Year Mortality in Spinal Metastatic Disease: Development and Internal Validation

Neurosurgery ◽

10.1093/neuros/nyz070 ◽

2019 ◽

Vol 85 (4) ◽

pp. E671-E681 ◽

Cited By ~ 22

Author(s):

Aditya V Karhade ◽

Quirina C B S Thio ◽

Paul T Ogink ◽

Christopher M Bono ◽

Marco L Ferrone ◽

...

Keyword(s):

Metastatic Disease ◽

Web Application ◽

Performance Status ◽

Predictive Performance ◽

Operative Management ◽

Stochastic Gradient ◽

Patient Specific ◽

Gradient Boosting ◽

Support Vector ◽

Stochastic Gradient Boosting

Abstract BACKGROUND Increasing prevalence of metastatic disease has been accompanied by increasing rates of surgical intervention. Current tools have poor to fair predictive performance for intermediate (90-d) and long-term (1-yr) mortality. OBJECTIVE To develop predictive algorithms for spinal metastatic disease at these time points and to provide patient-specific explanations of the predictions generated by these algorithms. METHODS Retrospective review was conducted at 2 large academic medical centers to identify patients undergoing initial operative management for spinal metastatic disease between January 2000 and December 2016. Five models (penalized logistic regression, random forest, stochastic gradient boosting, neural network, and support vector machine) were developed to predict 90-d and 1-yr mortality. RESULTS Overall, 732 patients were identified with 90-d and 1-yr mortality rates of 181 (25.1%) and 385 (54.3%), respectively. The stochastic gradient boosting algorithm had the best performance for 90-d mortality and 1-yr mortality. On global variable importance assessment, albumin, primary tumor histology, and performance status were the 3 most important predictors of 90-d mortality. The final models were incorporated into an open access web application able to provide predictions as well as patient-specific explanations of the results generated by the algorithms. The application can be found at https://sorg-apps.shinyapps.io/spinemetssurvival/ CONCLUSION Preoperative estimation of 90-d and 1-yr mortality was achieved with assessment of more flexible modeling techniques such as machine learning. Integration of these models into applications and patient-centered explanations of predictions represent opportunities for incorporation into healthcare systems as decision tools in the future.

Download Full-text

Combining GF-2 and Sentinel-2 Images to Detect Tree Mortality Caused by Red Turpentine Beetle during the Early Outbreak Stage in North China

Forests ◽

10.3390/f11020172 ◽

2020 ◽

Vol 11 (2) ◽

pp. 172 ◽

Cited By ~ 1

Author(s):

Zhan ◽

Yu ◽

Li ◽

Ren ◽

Gao ◽

...

Keyword(s):

Tree Mortality ◽

Spatial Scales ◽

Binary Classification ◽

Insect Pest ◽

Forest Stand ◽

Machine Learning Algorithms ◽

Classification And Regression Tree ◽

Support Vector ◽

Single Tree ◽

Sentinel 2

In recent years, the red turpentine beetle (RTB) (Dendroctonus valens LeConte) has invaded the northern regions of China. Due to the short invasion time, the outbreak of tree mortality corresponded to a low level of damage. Important information about tree mortality, provided by remote sensing at both single-tree and forest stand scale, is needed in forest management at the early stages of outbreak. In order to detect RTB-induced tree mortality at a single-tree scale, we evaluated the classification accuracies of Gaofen-2 (GF2) imagery at different spatial resolutions (1 and 4 m) using a pixel-based method. We also simultaneously applied an object-based method to 1 m pan-sharpened images. We used Sentinel-2 (S2) imagery with different resolutions (10 and 20 m) to detect RTB-induced tree mortality and compared their classification accuracies at a larger scale—the stand scale. Three kinds of machine learning algorithms—the classification and regression tree (CART), the random forest (RF), and the support vector machine (SVM)—were applied and compared in this study. The results showed that 1 m resolution GF2 images had the highest classification accuracy using the pixel-based method and SVM algorithm (overall accuracy = 77.7%). We found that the classification of three degrees of damage percentage within the S2 pixel (0%, <15%, and 15% < x < 50%) was not successful at a forest stand scale. However, 10 m resolution S2 images could acquire effective binary classification (<15%: overall accuracy = 74.9%; 15% < x < 50%: overall accuracy = 81.0%). Our results indicated that identifying tree mortality caused by RTB at a single-tree and forest stand scale was accomplished with the combination of GF2 and S2 images. Our results are very useful for the future exploration of the patterns of spatial and temporal changes in insect pest transmission at different spatial scales.

Download Full-text

Generating Up-to-Date Crop Maps Optimized for Sentinel-2 Imagery in Israel

Remote Sensing ◽

10.3390/rs13173488 ◽

2021 ◽

Vol 13 (17) ◽

pp. 3488

Author(s):

Keren Goldberg ◽

Ittai Herrmann ◽

Uri Hochberg ◽

Offer Rozenstein

Keyword(s):

Time Series ◽

Mean Shift ◽

Vegetation Indices ◽

Gradient Boosting ◽

Support Vector ◽

Object Based ◽

Accuracy Measure ◽

Extreme Gradient Boosting ◽

Accuracy Measures ◽

Sentinel 2

The overarching aim of this research was to develop a method for deriving crop maps from a time series of Sentinel-2 images between 2017 and 2018 to address global challenges in agriculture and food security. This study is the first step towards improving crop mapping based on phenological features retrieved from an object-based time series on a national scale. Five main crops in Israel were classified: wheat, barley, cotton, carrot, and chickpea. To optimize the object-based classification process, different characteristics and inputs of the mean shift segmentation algorithm were tested, including vegetation indices, three-band combinations, and high/low emphasis on the spatial and spectral characteristics. Four known vegetation indices (VIs)-based time series were tested. Additionally, we compared two widely used machine learning methods for crop classification, support vector machine (SVM) and random forest (RF), in addition to a newer classifier, extreme gradient boosting (XGBoost). Lastly, we examined two accuracy measures—overall accuracy (OA) and area under the curve (AUC)—in order to optimally estimate the accuracy in the case of imbalanced class representation. Mean shift best performed when emphasizing both the spectral and spatial characteristics while using the green, red, and near-infrared (NIR) bands as input. Both accuracy measures showed that RF and XGBoost classified different types of crops with significantly greater success than achieved by SVM. Nevertheless, AUC was better able to represent the significant differences between the classification algorithms than OA was. None of the VIs showed a significantly higher contribution to the classification. However, normalized difference infrared index (NDII) with XGBoost classifier showed the highest AUC results (88%). This study demonstrates that the short-wave infrared (SWIR) band with XGBoost improves crop type classification results. Furthermore, the study emphasizes the importance of addressing imbalanced classification datasets by using a proper accuracy measure. Since object-based classification and phenological features derived from a VI-based time series are widely used to produce crop maps, the current study is also relevant for operational agricultural management and informatics at large scales.

Download Full-text

Reliable photometric membership (RPM) of galaxies in clusters – I. A machine learning method and its performance in the local universe

Monthly Notices of the Royal Astronomical Society ◽

10.1093/mnras/staa486 ◽

2020 ◽

Vol 493 (3) ◽

pp. 3429-3441

Author(s):

Paulo A A Lopes ◽

André L B Ribeiro

Keyword(s):

Machine Learning ◽

Galaxy Evolution ◽

Large Scale ◽

Machine Learning Techniques ◽

Gradient Boosting ◽

Support Vector ◽

Validation Data ◽

Membership Probability ◽

Cluster Membership ◽

Stochastic Gradient Boosting

ABSTRACT We introduce a new method to determine galaxy cluster membership based solely on photometric properties. We adopt a machine learning approach to recover a cluster membership probability from galaxy photometric parameters and finally derive a membership classification. After testing several machine learning techniques (such as stochastic gradient boosting, model averaged neural network and k-nearest neighbours), we found the support vector machine algorithm to perform better when applied to our data. Our training and validation data are from the Sloan Digital Sky Survey main sample. Hence, to be complete to $M_r^* + 3$, we limit our work to 30 clusters with $z$phot-cl ≤ 0.045. Masses (M200) are larger than $\sim 0.6\times 10^{14} \, \mathrm{M}_{\odot }$ (most above $3\times 10^{14} \, \mathrm{M}_{\odot }$). Our results are derived taking in account all galaxies in the line of sight of each cluster, with no photometric redshift cuts or background corrections. Our method is non-parametric, making no assumptions on the number density or luminosity profiles of galaxies in clusters. Our approach delivers extremely accurate results (completeness, C $\sim 92{\rm{ per\ cent}}$ and purity, P $\sim 87{\rm{ per\ cent}}$) within R200, so that we named our code reliable photometric membership. We discuss possible dependencies on magnitude, colour, and cluster mass. Finally, we present some applications of our method, stressing its impact to galaxy evolution and cosmological studies based on future large-scale surveys, such as eROSITA, EUCLID, and LSST.

Download Full-text

Estimation of Leaf Chlorophyll a, b and Carotenoid Contents and Their Ratios Using Hyperspectral Reflectance

Remote Sensing ◽

10.3390/rs12193265 ◽

2020 ◽

Vol 12 (19) ◽

pp. 3265

Author(s):

Rei Sonobe ◽

Hiroto Yamashita ◽

Harumi Mihara ◽

Akio Morita ◽

Takashi Ikka

Keyword(s):

Chlorophyll A ◽

High Performance ◽

Machine Learning Algorithms ◽

Ion Concentration ◽

Gradient Boosting ◽

Support Vector ◽

Culture Methods ◽

Chl A ◽

Stochastic Gradient Boosting ◽

Processing Techniques

Japanese horseradish (wasabi) grows in very specific conditions, and recent environmental climate changes have damaged wasabi production. In addition, the optimal culture methods are not well known, and it is becoming increasingly difficult for incipient farmers to cultivate it. Chlorophyll a, b and carotenoid contents, as well as their allocation, could be an adequate indicator in evaluating its production and environmental stress; thus, developing an in situ method to monitor photosynthetic pigments based on reflectance could be useful for agricultural management. Besides original reflectance (OR), five pre-processing techniques, namely, first derivative reflectance (FDR), continuum-removed (CR), de-trending (DT), multiplicative scatter correction (MSC), and standard normal variate transformation (SNV), were compared to assess the accuracy of the estimation. Furthermore, five machine learning algorithms—random forest (RF), support vector machine (SVM), kernel-based extreme learning machine (KELM), Cubist, and Stochastic Gradient Boosting (SGB)—were considered. To classify the samples under different pH or sulphur ion concentration conditions, the end of the red edge bands was effective for OR, FDR, DT, MSC, and SNV, while a green-peak band was effective for CR. Overall, KELM and Cubist showed high performance and incorporating pre-processing techniques was effective for obtaining estimated values with high accuracy. The best combinations were found to be DT–KELM for chl a (RPD = 1.511–5.17, RMSE = 1.23–3.62 μg cm−2) and chl a:b (RPD = 0.73–3.17, RMSE = 0.13–0.60); CR–KELM for chl b (RPD = 1.92–5.06, RMSE = 0.41–1.03 μg cm−2) and chl a:car (RPD = 1.31–3.23, RMSE = 0.26–0.50); SNV–Cubist for car (RPD = 1.63–3.32, RMSE = 0.31–1.89 μg cm−2); and DT–Cubist for chl:car (RPD = 1.53–3.96, RMSE = 0.27–0.74).

Download Full-text

Cloud and Cloud-Shadow Detection for Applications in Mapping Small-Scale Mining in Colombia Using Sentinel-2 Imagery

Remote Sensing ◽

10.3390/rs13040736 ◽

2021 ◽

Vol 13 (4) ◽

pp. 736

Author(s):

Elsy Ibrahim ◽

Jingyi Jiang ◽

Luisa Lema ◽

Pierre Barnabé ◽

Gregory Giuliani ◽

...

Keyword(s):

Rural Areas ◽

Bare Soil ◽

Shadow Detection ◽

Cloud Base ◽

Support Vector ◽

Small Scale ◽

Mining Sites ◽

Mining Areas ◽

Sensor Geometry ◽

Sentinel 2

Small-scale placer mining in Colombia takes place in rural areas and involves excavations resulting in large footprints of bare soil and water ponds. Such excavated areas comprise a mosaic of challenging terrains for cloud and cloud-shadow detection of Sentinel-2 (S2A and S2B) data used to identify, map, and monitor these highly dynamic activities. This paper uses an efficient two-step machine-learning approach using freely available tools to detect clouds and shadows in the context of mapping small-scale mining areas, one which places an emphasis on the reduction of misclassification of mining sites as clouds or shadows. The first step is comprised of a supervised support-vector-machine classification identifying clouds, cloud shadows, and clear pixels. The second step is a geometry-based improvement of cloud-shadow detection where solar-cloud-shadow-sensor geometry is used to exclude commission errors in cloud shadows. The geometry-based approach makes use of sun angles and sensor view angles available in Sentinel-2 metadata to identify potential directions of cloud shadow for each cloud projection. The approach does not require supplementary data on cloud-top or bottom heights nor cloud-top ruggedness. It assumes that the location of dense clouds is mainly impacted by meteorological conditions and that cloud-top and cloud-base heights vary in a predefined manner. The methodology has been tested over an intensively excavated and well-studied pilot site and shows 50% more detection of clouds and shadows than Sen2Cor. Furthermore, it has reached a Specificity of 1 in the correct detection of mining sites and water ponds, proving itself to be a reliable approach for further related studies on the mapping of small-scale mining in the area. Although the methodology was tailored to the context of small-scale mining in the region of Antioquia, it is a scalable approach and can be adapted to other areas and conditions.

Download Full-text

Predict Health Insurance Cost by using Machine Learning and DNN Regression Models

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.c8364.0110321 ◽

2021 ◽

Vol 10 (2) ◽

pp. 137-143

Author(s):

Mohamed hanafy ◽

Omar M. A. Mahmoud

Keyword(s):

Machine Learning ◽

Insurance Industry ◽

Additive Model ◽

Policy Formulation ◽

Stochastic Gradient ◽

Gradient Boosting ◽

Support Vector ◽

K Nearest Neighbors ◽

Stochastic Gradient Boosting ◽

Insurance Cost

Insurance is a policy that eliminates or decreases loss costs occurred by various risks. Various factors influence the cost of insurance. These considerations contribute to the insurance policy formulation. Machine learning (ML) for the insurance industry sector can make the wording of insurance policies more efficient. This study demonstrates how different models of regression can forecast insurance costs. And we will compare the results of models, for example, Multiple Linear Regression, Generalized Additive Model, Support Vector Machine, Random Forest Regressor, CART, XGBoost, k-Nearest Neighbors, Stochastic Gradient Boosting, and Deep Neural Network. This paper offers the best approach to the Stochastic Gradient Boosting model with an MAE value of 0.17448, RMSE value of 0.38018and R -squared value of 85.8295.

Download Full-text