scholarly journals CROP CLASSIFICATION ON SINGLE DATE SENTINEL-2 IMAGERY USING RANDOM FOREST AND SUPPOR VECTOR MACHINE

2018 ◽  
Vol XLII-5 ◽  
pp. 683-688 ◽  
Author(s):  
R. Saini ◽  
S. K. Ghosh
Keyword(s):  
Random Forest ◽  
Near Infrared ◽  
Vegetation Mapping ◽  
Good Choice ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Tuning Parameters ◽  
Spectral Bands ◽  
Fodder Crops ◽  
Sentinel 2

<p><strong>Abstract.</strong> Mapping of the crop using satellite images is a challenging task due to complexities within field, and having the similar spectral properties with other crops in the region. Recently launched Sentinel-2 satellite has thirteen spectral bands, fast revisit time and resolution at three different level (10<span class="thinspace"></span>m, 20<span class="thinspace"></span>m, 60<span class="thinspace"></span>m), as well as the free availability of data, makes it a good choice for vegetation mapping. This study aims to classify crop using single date Sentinel-2 imagery in the Roorkee, district Haridwar, Uttarakhand, India. Classification is performed by using two most popular and efficient machine learning algorithms: Random Forest (RF) and Support Vector Machine (SVM). In this study, four spectral bands, i.e., Near Infrared, Red, Green, and Blue of Sentinel-2 satellite are stacked for the classification. Results show that overall accuracy of the classification achieved by RF and SVM using Sentinel-2 imagery are 84.22% and 81.85% respectively. This study demonstrates that both classifiers performed well by setting an optimal value of tuning parameters, but RF achieved 2.37% higher overall accuracy over SVM. Analysis of the results states that the class specific accuracies of High-Density Forest attain the highest accuracy whereas Fodder class reports the lowest accuracy. Fodder achieve lowest accuracy because there is an intermixing of pixels among Wheat and Fodder crops. In this study, it is found that RF shows better potential in classifying crops more accurately in comparison to SVM and Sentinel-2 has great potential in vegetation mapping domain in remote sensing.</p>

scholarly journals A Machine Learning Approach for Mapping Forest Vegetation in Riparian Zones in an Atlantic Biome Environment Using Sentinel-2 Imagery

2020 ◽  
Vol 12 (24) ◽  
pp. 4086
Author(s):  
Danielle Elis Garcia Furuya ◽  
João Alex Floriano Aguiar ◽  
Nayara V. Estrabis ◽  
Mayara Maezano Faita Pinheiro ◽  
Michelle Taís Garcia Furuya ◽  
...  
Keyword(s):  
Machine Learning ◽  
Environmental Planning ◽  
Riparian Zone ◽  
Learning Algorithms ◽  
Vegetation Mapping ◽  
Forest Vegetation ◽  
Machine Learning Algorithms ◽  
Riparian Zones ◽  
Support Vector ◽  
Sentinel 2

Riparian zones consist of important environmental regions, specifically to maintain the quality of water resources. Accurately mapping forest vegetation in riparian zones is an important issue, since it may provide information about numerous surface processes that occur in these areas. Recently, machine learning algorithms have gained attention as an innovative approach to extract information from remote sensing imagery, including to support the mapping task of vegetation areas. Nonetheless, studies related to machine learning application for forest vegetation mapping in the riparian zones exclusively is still limited. Therefore, this paper presents a framework for forest vegetation mapping in riparian zones based on machine learning models using orbital multispectral images. A total of 14 Sentinel-2 images registered throughout the year, covering a large riparian zone of a portion of a wide river in the Pontal do Paranapanema region, São Paulo state, Brazil, was adopted as the dataset. This area is mainly composed of the Atlantic Biome vegetation, and it is near to the last primary fragment of its biome, being an important region from the environmental planning point of view. We compared the performance of multiple machine learning algorithms like decision tree (DT), random forest (RF), support vector machine (SVM), and normal Bayes (NB). We evaluated different dates and locations with all models. Our results demonstrated that the DT learner has, overall, the highest accuracy in this task. The DT algorithm also showed high accuracy when applied on different dates and in the riparian zone of another river. We conclude that the proposed approach is appropriated to accurately map forest vegetation in riparian zones, including temporal context.

scholarly journals Wheat Crop Acreage Estimation Based on Remote Sensing and GIS in Jabalpur (Madhya Pradesh, India)

2021 ◽  
pp. 88-94
Author(s):  
Umakant Rawat ◽  
Ankit Yadav ◽  
P.S. Pawar ◽  
Aniket Rajput ◽  
Devendra Vasht ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Near Infrared ◽  
Unsupervised Classification ◽  
Good Choice ◽  
Madhya Pradesh ◽  
Wheat Crop ◽  
Kappa Statistics ◽  
Crop Acreage ◽  
Spectral Bands ◽  
Sentinel 2

Mapping and classification crop by using satellite images is a challenging task that can minimize the complexities of field visits. The recently launched Sentinel-2 satellite has thirteen spectral bands, short revisit time and determination at three different resolutions (10 m, 20 m and 60 m), besides that, the free availability of the images makes it a good choice for vegetation mapping. This study aims to classify crop, using single date Sentinel-2 imagery within the Jabalpur, state of Madhya Pradesh, India. The classification was performed by using Unsupervised Classification. In this study, four spectral bands, i.e., Near Infrared, Red, Green, and Blue of Sentinel-2 were stacked for the classification. The results show that the area of wheat crop corresponds to 83.07%; Gram/ Pulses, 14.64%; and other crop, 2.28%. The overall accuracy and overall Kappa Statistics of the classification using Sentinel-2 imagery are 85.71% and 0.819%, respectively. Therefore, this study has found that Sentinel-2 presented great potential in the mapping of the agriculture areas of Jabalpur by remote sensing.

scholarly journals VEGETATION MAPPING OF SENTINEL-1 AND 2 SATELLITE IMAGES USING CONVOLUTIONAL NEURAL NETWORK AND RANDOM FOREST WITH THE AID OF DUAL-POLARIZED AND OPTICAL VEGETATION INDEXES

2019 ◽  
Vol XLII-4/W18 ◽  
pp. 435-440
Author(s):  
N. Ghasemian Sorboni ◽  
P. Pahlavani ◽  
B. Bigdeli
Keyword(s):  
Remote Sensing ◽  
Random Forest ◽  
Vegetation Index ◽  
Near Infrared ◽  
False Positive Rate ◽  
Vegetation Mapping ◽  
Vegetation Indexes ◽  
Positive Rate ◽  
Dual Polarized ◽  
Sentinel 2

Abstract. Vegetation mapping is one of the most critical challenges of remote sensing society in forestry applications. Sentinel-1 dataset has the potential of vegetation mapping, but because of its limited number of polarizations, full polarized vegetation indexes are not accessible. The Sentinel-2 dataset is more suitable for vegetation mapping because a wide variety of vegetation indexes can be extracted from them. Handling this large number of vegetation indexes needs a robust feature extractor. Convolutional Neural Networks (CNN) extract relevant features through their deep feature layers structure and throw out disturbances from small to large scales. Hence, they can be far useful for classifying remote sensing data when the number of input bands is considerable. After pre-processing Sentinel-1 and 2 datasets and extracting the dual-polarized and optical vegetation indexes, we fed the sentinel-1 vegetation indexes alongside the VV and VH sigma Nought bands to a Random Forest (RF) and 1D CNN classifier. Also, 13 spectral features of the Sentinel-2 and the extracted indexes like Blue Ratio (BR), Vegetation index based on Red Edge (VIRE) and Normalized Near Infrared (NNIR) were imported to a RF and 1D CNN. The classification result of Sentinel-1 data showed that Dual Polarized Soil Vegetation Index (DPSVI) is a good indicator for discriminating vegetation pixels. Also, the experiment on the Sentinel-2 dataset using 1D CNN resulted in True Positive Rate (TPR) and False Positive Rate of 0.839 and 0.034, respectively.

scholarly journals Delineating Smallholder Maize Farms from Sentinel-1 Coupled with Sentinel-2 Data Using Machine Learning

2021 ◽  
Vol 13 (9) ◽  
pp. 4728
Author(s):  
Zinhle Mashaba-Munghemezulu ◽  
George Johannes Chirima ◽  
Cilence Munghemezulu
Keyword(s):  
Machine Learning ◽  
Food Security ◽  
Rural Communities ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Subsistence Agriculture ◽  
Smallholder Farms ◽  
Main Driver ◽  
Sentinel 2

Rural communities rely on smallholder maize farms for subsistence agriculture, the main driver of local economic activity and food security. However, their planted area estimates are unknown in most developing countries. This study explores the use of Sentinel-1 and Sentinel-2 data to map smallholder maize farms. The random forest (RF), support vector (SVM) machine learning algorithms and model stacking (ST) were applied. Results show that the classification of combined Sentinel-1 and Sentinel-2 data improved the RF, SVM and ST algorithms by 24.2%, 8.7%, and 9.1%, respectively, compared to the classification of Sentinel-1 data individually. Similarities in the estimated areas (7001.35 ± 1.2 ha for RF, 7926.03 ± 0.7 ha for SVM and 7099.59 ± 0.8 ha for ST) show that machine learning can estimate smallholder maize areas with high accuracies. The study concludes that the single-date Sentinel-1 data were insufficient to map smallholder maize farms. However, single-date Sentinel-1 combined with Sentinel-2 data were sufficient in mapping smallholder farms. These results can be used to support the generation and validation of national crop statistics, thus contributing to food security.

scholarly journals Statistical and Electrical Features Evaluation for Electrical Appliances Energy Disaggregation

2019 ◽  
Vol 11 (11) ◽  
pp. 3222 ◽  
Author(s):  
Pascal Schirmer ◽  
Iosif Mporas
Keyword(s):  
Random Forest ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Random Forest Regression ◽  
Nearest Neighbours ◽  
Energy Disaggregation ◽  
Vector Machines ◽  
Non Linear ◽  
Load Monitoring ◽  
Sinusoidal Current

In this paper we evaluate several well-known and widely used machine learning algorithms for regression in the energy disaggregation task. Specifically, the Non-Intrusive Load Monitoring approach was considered and the K-Nearest-Neighbours, Support Vector Machines, Deep Neural Networks and Random Forest algorithms were evaluated across five datasets using seven different sets of statistical and electrical features. The experimental results demonstrated the importance of selecting both appropriate features and regression algorithms. Analysis on device level showed that linear devices can be disaggregated using statistical features, while for non-linear devices the use of electrical features significantly improves the disaggregation accuracy, as non-linear appliances have non-sinusoidal current draw and thus cannot be well parametrized only by their active power consumption. The best performance in terms of energy disaggregation accuracy was achieved by the Random Forest regression algorithm.

scholarly journals Feature Selection and Comparison of Machine Learning Algorithms in Classification of Grazing and Rumination Behaviour in Sheep

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3532 ◽  
Author(s):  
Nicola Mansbridge ◽  
Jurgen Mitsch ◽  
Nicola Bollard ◽  
Keith Ellis ◽  
Giuliana Miguel-Pacheco ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Time Budget ◽  
Learning Algorithms ◽  
Eating Behaviour ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Optimum Number ◽  
Eating Behaviours ◽  
Adaptive Boosting

Grazing and ruminating are the most important behaviours for ruminants, as they spend most of their daily time budget performing these. Continuous surveillance of eating behaviour is an important means for monitoring ruminant health, productivity and welfare. However, surveillance performed by human operators is prone to human variance, time-consuming and costly, especially on animals kept at pasture or free-ranging. The use of sensors to automatically acquire data, and software to classify and identify behaviours, offers significant potential in addressing such issues. In this work, data collected from sheep by means of an accelerometer/gyroscope sensor attached to the ear and collar, sampled at 16 Hz, were used to develop classifiers for grazing and ruminating behaviour using various machine learning algorithms: random forest (RF), support vector machine (SVM), k nearest neighbour (kNN) and adaptive boosting (Adaboost). Multiple features extracted from the signals were ranked on their importance for classification. Several performance indicators were considered when comparing classifiers as a function of algorithm used, sensor localisation and number of used features. Random forest yielded the highest overall accuracies: 92% for collar and 91% for ear. Gyroscope-based features were shown to have the greatest relative importance for eating behaviours. The optimum number of feature characteristics to be incorporated into the model was 39, from both ear and collar data. The findings suggest that one can successfully classify eating behaviours in sheep with very high accuracy; this could be used to develop a device for automatic monitoring of feed intake in the sheep sector to monitor health and welfare.

scholarly journals Deep learning para la clasificación de usos de suelo agrícola con Sentinel-2

2020 ◽  
pp. 35
Author(s):  
M. Campos-Taberner ◽  
F.J. García-Haro ◽  
B. Martínez ◽  
M.A. Gilabert
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Near Infrared ◽  
Spatial Information ◽  
Learning Algorithm ◽  
Support Vector ◽  
Sensing Applications ◽  
Learning Techniques ◽  
Remote Sensing Applications ◽  
Sentinel 2

<p class="p1">The use of deep learning techniques for remote sensing applications has recently increased. These algorithms have proven to be successful in estimation of parameters and classification of images. However, little effort has been made to make them understandable, leading to their implementation as “black boxes”. This work aims to evaluate the performance and clarify the operation of a deep learning algorithm, based on a bi-directional recurrent network of long short-term memory (2-BiLSTM). The land use classification in the Valencian Community based on Sentinel-2 image time series in the framework of the common agricultural policy (CAP) is used as an example. It is verified that the accuracy of the deep learning techniques is superior (98.6 % overall success) to that other algorithms such as decision trees (DT), k-nearest neighbors (k-NN), neural networks (NN), support vector machines (SVM) and random forests (RF). The performance of the classifier has been studied as a function of time and of the predictors used. It is concluded that, in the study area, the most relevant information used by the network in the classification are the images corresponding to summer and the spectral and spatial information derived from the red and near infrared bands. These results open the door to new studies in the field of the explainable deep learning in remote sensing applications.</p>

scholarly journals Techniques for Detecting Malware Traffic: A Comprehensive Approach to Feature Selection and Classification

2021 ◽  
Vol 9 (12) ◽  
pp. 1-10
Author(s):  
Harsha A K
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Random Forest ◽  
Learning Algorithms ◽  
Malware Detection ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Support Vector ◽  
Steady Increase ◽  
Extreme Gradient Boosting

Abstract: Since the advent of encryption, there has been a steady increase in malware being transmitted over encrypted networks. Traditional approaches to detect malware like packet content analysis are inefficient in dealing with encrypted data. In the absence of actual packet contents, we can make use of other features like packet size, arrival time, source and destination addresses and other such metadata to detect malware. Such information can be used to train machine learning classifiers in order to classify malicious and benign packets. In this paper, we offer an efficient malware detection approach using classification algorithms in machine learning such as support vector machine, random forest and extreme gradient boosting. We employ an extensive feature selection process to reduce the dimensionality of the chosen dataset. The dataset is then split into training and testing sets. Machine learning algorithms are trained using the training set. These models are then evaluated against the testing set in order to assess their respective performances. We further attempt to tune the hyper parameters of the algorithms, in order to achieve better results. Random forest and extreme gradient boosting algorithms performed exceptionally well in our experiments, resulting in area under the curve values of 0.9928 and 0.9998 respectively. Our work demonstrates that malware traffic can be effectively classified using conventional machine learning algorithms and also shows the importance of dimensionality reduction in such classification problems. Keywords: Malware Detection, Extreme Gradient Boosting, Random Forest, Feature Selection.

Abstract 15895: Machine Learning Algorithms to Predict Major Adverse Cardiovascular Events in Patients Undergoing Orthotopic Liver Transplantation: A Retrospective Cohort Study

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
vardhmaan jain ◽  
Vikram Sharma ◽  
Agam Bansal ◽  
Cerise Kleb ◽  
Chirag Sheth ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Cardiovascular Events ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Major Adverse Cardiovascular Events ◽  
Support Vector ◽  
Post Transplant ◽  
Extreme Gradient Boosting ◽  
All Cause Mortality

Background: Post-transplant major adverse cardiovascular events (MACE) are amongst the leading cause of death amongst orthotopic liver transplant(OLT) recipients. Despite years of guideline directed therapy, there are limited data on predictors of post-OLT MACE. We assessed if machine learning algorithms (MLA) can predict MACE and all-cause mortality in patients undergoing OLT. Methods: We tested three MLA: support vector machine, extreme gradient boosting(XG-Boost) and random forest with traditional logistic regression for prediction of MACE and all-cause mortality on a cohort of consecutive patients undergoing OLT at our center between 2008-2019. The cohort was randomly split into a training (80%) and testing (20%) cohort. Model performance was assessed using c-statistic or AUC. Results: We included 1,459 consecutive patients with mean ± SD age 54.2 ± 13.8 years, 32% female who underwent OLT. There were 199 (13.6%) MACE and 289 (20%) deaths at a mean follow up of 4.56 ± 3.3 years. The random forest MLA was the best performing model for predicting MACE [AUC:0.78, 95% CI: 0.70-0.85] as well as mortality [AUC:0.69, 95% CI: 0.61-0.76], with all models performing better when predicting MACE vs mortality. See Table and Figure. Conclusion: Random forest machine learning algorithms were more predictive and discriminative than traditional regression models for predicting major adverse cardiovascular events and all-cause mortality in patients undergoing OLT. Validation and subsequent incorporation of MLA in clinical decision making for OLT candidacy could help risk stratify patients for post-transplant adverse cardiovascular events.

scholarly journals A Deep Learning Approach for Burned Area Segmentation with Sentinel-2 Data

2020 ◽  
Vol 12 (15) ◽  
pp. 2422
Author(s):  
Lisa Knopp ◽  
Marc Wieland ◽  
Michaela Rättich ◽  
Sandro Martinis
Keyword(s):  
Deep Learning ◽  
Network Performance ◽  
Near Infrared ◽  
Remote Sensing Data ◽  
Economic Consequences ◽  
Validation Dataset ◽  
Burned Area ◽  
Burned Areas ◽  
Spectral Bands ◽  
Sentinel 2

Wildfires have major ecological, social and economic consequences. Information about the extent of burned areas is essential to assess these consequences and can be derived from remote sensing data. Over the last years, several methods have been developed to segment burned areas with satellite imagery. However, these methods mostly require extensive preprocessing, while deep learning techniques—which have successfully been applied to other segmentation tasks—have yet to be fully explored. In this work, we combine sensor-specific and methodological developments from the past few years and suggest an automatic processing chain, based on deep learning, for burned area segmentation using mono-temporal Sentinel-2 imagery. In particular, we created a new training and validation dataset, which is used to train a convolutional neural network based on a U-Net architecture. We performed several tests on the input data and reached optimal network performance using the spectral bands of the visual, near infrared and shortwave infrared domains. The final segmentation model achieved an overall accuracy of 0.98 and a kappa coefficient of 0.94.

Sign in / Sign up

Export Citation Format

Share Document