Research on the classification methods of ecosystem service of soil retention for large-scale choropleth mapping

2021 ◽  
Vol 41 (4) ◽  
Author(s):  
张丹红，王效科，张路，黄斌斌 ZHANG Danhong
Keyword(s):  
Ecosystem Service ◽  
Large Scale ◽  
Classification Methods ◽  
Choropleth Mapping ◽  
Soil Retention

scholarly journals A Novel Unsupervised Classification Method for Sandy Land Using Fully Polarimetric SAR Data

2021 ◽  
Vol 13 (3) ◽  
pp. 355
Author(s):  
Weixian Tan ◽  
Borong Sun ◽  
Chenyu Xiao ◽  
Pingping Huang ◽  
Wei Xu ◽  
...  
Keyword(s):  
Spectral Clustering ◽  
Large Scale ◽  
Clustering Algorithm ◽  
Feature Vector ◽  
Unsupervised Classification ◽  
Classification Method ◽  
Sandy Land ◽  
Classification Methods ◽  
The Many ◽  
Representative Points

Classification based on polarimetric synthetic aperture radar (PolSAR) images is an emerging technology, and recent years have seen the introduction of various classification methods that have been proven to be effective to identify typical features of many terrain types. Among the many regions of the study, the Hunshandake Sandy Land in Inner Mongolia, China stands out for its vast area of sandy land, variety of ground objects, and intricate structure, with more irregular characteristics than conventional land cover. Accounting for the particular surface features of the Hunshandake Sandy Land, an unsupervised classification method based on new decomposition and large-scale spectral clustering with superpixels (ND-LSC) is proposed in this study. Firstly, the polarization scattering parameters are extracted through a new decomposition, rather than other decomposition approaches, which gives rise to more accurate feature vector estimate. Secondly, a large-scale spectral clustering is applied as appropriate to meet the massive land and complex terrain. More specifically, this involves a beginning sub-step of superpixels generation via the Adaptive Simple Linear Iterative Clustering (ASLIC) algorithm when the feature vector combined with the spatial coordinate information are employed as input, and subsequently a sub-step of representative points selection as well as bipartite graph formation, followed by the spectral clustering algorithm to complete the classification task. Finally, testing and analysis are conducted on the RADARSAT-2 fully PolSAR dataset acquired over the Hunshandake Sandy Land in 2016. Both qualitative and quantitative experiments compared with several classification methods are conducted to show that proposed method can significantly improve performance on classification.

scholarly journals Applying Machine Learning for Improving Performance Classification on Driving Behavior

2021 ◽  
Vol 4 (1) ◽  
pp. 8
Author(s):  
Ahmad Iwan Fadli ◽  
Selo Sulistyo ◽  
Sigit Wibowo
Keyword(s):  
Machine Learning ◽  
Traffic Accident ◽  
Large Scale ◽  
Detection System ◽  
Difficult Problem ◽  
Sensor Data ◽  
Driving Safety ◽  
Support Vector ◽  
Classification Methods ◽  
Machine Learning Classification

Traffic accident is a very difficult problem to handle on a large scale in a country. Indonesia is one of the most populated, developing countries that use vehicles for daily activities as its main transportation.  It is also the country with the largest number of car users in Southeast Asia, so driving safety needs to be considered. Using machine learning classification method to determine whether a driver is driving safely or not can help reduce the risk of driving accidents. We created a detection system to classify whether the driver is driving safely or unsafely using trip sensor data, which include Gyroscope, Acceleration, and GPS. The classification methods used in this study are Random Forest (RF) classification algorithm, Support Vector Machine (SVM), and Multilayer Perceptron (MLP) by improving data preprocessing using feature extraction and oversampling methods. This study shows that RF has the best performance with 98% accuracy, 98% precision, and 97% sensitivity using the proposed preprocessing stages compared to SVM or MLP.

scholarly journals Are open set classification methods effective on large-scale datasets?

PLoS ONE ◽  
2020 ◽  
Vol 15 (9) ◽  
pp. e0238302 ◽  
Author(s):  
Ryne Roady ◽  
Tyler L. Hayes ◽  
Ronald Kemker ◽  
Ayesha Gonzales ◽  
Christopher Kanan
Keyword(s):  
Large Scale ◽  
Classification Methods ◽  
Open Set

scholarly journals Dissecting the ecosystem service of large-scale pollutant retention: The role of wetlands and other landscape features

AMBIO ◽  
2015 ◽  
Vol 44 (S1) ◽  
pp. 127-137 ◽  
Author(s):  
Andrew Quin ◽  
Fernando Jaramillo ◽  
Georgia Destouni
Keyword(s):  
Ecosystem Service ◽  
Large Scale ◽  
Landscape Features

scholarly journals Impacts of Dynamical Downscaling on Circulation type Statistics: Potential added Value in the Euro-CORDEX Ensemble

2021 ◽  
Author(s):  
Julie Røste ◽  
Oskar A Landgren
Keyword(s):  
Large Scale ◽  
Climate Model ◽  
Dynamical Downscaling ◽  
Regional Climate ◽  
Circulation Type ◽  
Global Model ◽  
Added Value ◽  
Classification Methods ◽  
Circulation Types ◽  
Climate Model Simulations

Abstract Atmospheric circulation type classification methods were applied to an ensemble of 57 regional climate model simulations from Euro-CORDEX, their 11 boundary models from CMIP5 and the ERA5 reanalysis. We compared frequencies of the different circulation types in the simulations with ERA5 and found that the regional models add value especially in the summer season. We applied three different classification methods (the subjective Grosswettertypes and the two optimisation algorithms SANDRA and distributed k-means clustering) from the cost733class software and found that the results are not particularly sensitive to choice of circulation classification method. There are large differences between models. Simulations based on MIROC-MIROC5 and CNRM-CERFACS-CNRM-CM5 show an over-representation of easterly flow and an under-representation of westerly. The downscaled results retain the large-scale circulation from the global model most days, but especially the regional model IPSL-WRF381P changes the circulation more often, which increases the error relative to ERA5. Simulations based on ICHEC-EC-EARTH and MPI-M-MPI-ESM-LR show consistently smaller errors relative to ERA5 in all seasons. The ensemble spread is largest in the summer and smallest in the winter. Under the future RCP8.5 scenario, more than half of the ensemble shows an increase in frequency of north-easterly flow and decrease in the Central-Eastern European high and south-easterly flow. There is in general a strong agreement in the sign of the change between the regional simulations and the data from the corresponding global model.

scholarly journals Reproducible evaluation of classification methods in Alzheimer’s disease: framework and application to MRI and PET data

2018 ◽  
Author(s):  
Jorge Samper-González ◽  
Ninon Burgos ◽  
Simona Bottani ◽  
Sabrina Fontanella ◽  
Pascal Lu ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Feature Extraction ◽  
Fdg Pet ◽  
Large Scale ◽  
Extraction Methods ◽  
Classification Performance ◽  
Evaluation Framework ◽  
Classification Methods ◽  
Standard Format

AbstractA large number of papers have introduced novel machine learning and feature extraction methods for automatic classification of Alzheimer’s disease (AD). However, while the vast majority of these works use the public dataset ADNI for evaluation, they are difficult to reproduce because different key components of the validation are often not readily available. These components include selected participants and input data, image preprocessing and cross-validation procedures. The performance of the different approaches is also difficult to compare objectively. In particular, it is often difficult to assess which part of the method (e.g. preprocessing, feature extraction or classification algorithms) provides a real improvement, if any. In the present paper, we propose a framework for reproducible and objective classification experiments in AD using three publicly available datasets (ADNI, AIBL and OASIS). The framework comprises: i) automatic conversion of the three datasets into a standard format (BIDS); ii) a modular set of preprocessing pipelines, feature extraction and classification methods, together with an evaluation framework, that provide a baseline for benchmarking the different components. We demonstrate the use of the framework for a large-scale evaluation on 1960 participants using T1 MRI and FDG PET data. In this evaluation, we assess the influence of different modalities, preprocessing, feature types (regional or voxel-based features), classifiers, training set sizes and datasets. Performances were in line with the state-of-the-art. FDG PET outperformed T1 MRI for all classification tasks. No difference in performance was found for the use of different atlases, image smoothing, partial volume correction of FDG PET images, or feature type. Linear SVM and L2-logistic regression resulted in similar performance and both outperformed random forests. The classification performance increased along with the number of subjects used for training. Classifiers trained on ADNI generalized well to AIBL and OASIS, performing better than the classifiers trained and tested on each of these datasets independently. All the code of the framework and the experiments is publicly available.

scholarly journals Assessment on the Soil Retention Service of Water Erosion in the Nile River Basin Considering Vegetation Factor Variance from 1982 to 2013

Water ◽  
2020 ◽  
Vol 12 (7) ◽  
pp. 2018
Author(s):  
Hua Liu ◽  
Wenwu Zhao ◽  
Yanxu Liu
Keyword(s):  
River Basin ◽  
Large Scale ◽  
Water Erosion ◽  
Estimation Methods ◽  
Nile River ◽  
Negative Effects ◽  
Soil Retention ◽  
Nile River Basin ◽  
Factor C ◽  
Selection Of

Water erosion has negative effects on agricultural productivity in Africa. The cover management factor (C factor) related to vegetation is the most influential parameter in the estimation of water erosion and reflects key interrelated cover and management information on the soil retention service of water erosion. However, the estimations of C factor on a large-scale display large differences. The Nile River Basin has suffered severe water erosion for several decades, while the soil retention service of water erosion from vegetation is still unclear. This study assesses the spatiotemporal change in soil retention service in the Nile River Basin from 1982 to 2013, based on the Revised Universal Soil Loss Equation (RUSLE) model. The comparison of six kinds of estimation methods showed that four methods could be used, whereas the other two were inappropriate. The average annual soil retention service based on the C factor variance ranged from 934.08–1240.56 (t ha−1 y−1), and spatially increased from south to north. The area of significant increasing and decreasing tendencies were 1.31 × 104–1.94 × 105 km2 and 5.68 × 103–3.81 × 104 km2, respectively. These results provide a reference for the selection of C factor methods and spatiotemporal evidence of the soil retention service of water erosion in the Nile River Basin.

Sign in / Sign up

Export Citation Format

Share Document