scholarly journals Land-Cover Classification Using MaxEnt: Can We Trust in Model Quality Metrics for Estimating Classification Accuracy?

Entropy ◽  
2020 ◽  
Vol 22 (3) ◽  
pp. 342 ◽  
Author(s):  
Narkis S. Morales ◽  
Ignacio C. Fernández
Keyword(s):  
Land Cover ◽  
Species Distribution ◽  
Classification Accuracy ◽  
Land Cover Classification ◽  
Quality Metrics ◽  
Quality Model ◽  
Distribution Models ◽  
Model Quality ◽  
Single Class ◽  
Land Covers

MaxEnt is a popular maximum entropy-based algorithm originally developed for modelling species distribution, but increasingly used for land-cover classification. In this article, we used MaxEnt as a single-class land-cover classification and explored if recommended procedures for generating high-quality species distribution models also apply for generating high-accuracy land-cover classification. We used remote sensing imagery and randomly selected ground-true points for four types of land covers (built, grass, deciduous, evergreen) to generate 1980 classification maps using MaxEnt. We calculated different accuracy discrimination and quality model metrics to determine if these metrics were suitable proxies for estimating the accuracy of land-cover classification outcomes. Correlation analysis between model quality metrics showed consistent patterns for the relationships between metrics, but not for all land-covers. Relationship between model quality metrics and land-cover classification accuracy were land-cover-dependent. While for built cover there was no consistent patterns of correlations for any quality metrics; for grass, evergreen and deciduous, there was a consistent association between quality metrics and classification accuracy. We recommend evaluating the accuracy of land-cover classification results by using proper discrimination accuracy coefficients (e.g., Kappa, Overall Accuracy), and not placing all the confidence in model’s quality metrics as a reliable indicator of land-cover classification results.

scholarly journals One-class land-cover classification using MaxEnt: the effect of modelling parameterization on classification accuracy

PeerJ ◽  
2019 ◽  
Vol 7 ◽  
pp. e7016 ◽  
Author(s):  
Ignacio C. Fernández ◽  
Narkis S. Morales
Keyword(s):  
Land Cover ◽  
Classification Accuracy ◽  
Land Cover Classification ◽  
Deciduous Trees ◽  
Marginal Effect ◽  
Sampling Points ◽  
Logarithmic Distribution ◽  
Efficient Alternative ◽  
Land Covers ◽  
One Class Classification

Multiple-class land-cover classification approaches can be inefficient when the main goal is to classify only one or a few classes. Under this scenario one-class classification algorithms could be a more efficient alternative. Currently there are several algorithms that can fulfil this task, with MaxEnt being one of the most promising. However, there is scarce information regarding parametrization for performing land-cover classification using MaxEnt. In this study we aimed to understand how MaxEnt parameterization affects the classification accuracy of four different land-covers (i.e., built-up, irrigated grass, evergreen trees and deciduous trees) in the city of Santiago de Chile. We also evaluated if MaxEnt manual parameterization outperforms classification results obtained when using MaxEnt default parameters setting. To accomplish our objectives, we generated a set of 25,344 classification maps (i.e., 6,336 for each assessed land-cover), which are based on all the potential combination of 12 different classes of features restrictions, four regularization multipliers, four different sample sizes, three training/testing proportions, and 11 thresholds for generating the binary maps. Our results showed that with a good parameterization, MaxEnt can effectively classify different land covers with kappa values ranging from 0.68 for deciduous trees to 0.89 for irrigated grass. However, the accuracy of classification results is highly influenced by the type of land-cover being classified. Simpler models produced good classification outcomes for homogenous land-covers, but not for heterogeneous covers, where complex models provided better outcomes. In general, manual parameterization improves the accuracy of classification results, but this improvement will depend on the threshold used to generate the binary map. In fact, threshold selection showed to be the most relevant factor impacting the accuracy of the four land-cover classification. The number of sampling points for training the model also has a positive effect on classification results. However, this effect followed a logarithmic distribution, showing an improvement of kappa values when increasing the sampling from 40 to 60 points, but showing only a marginal effect if more than 60 sampling points are used. In light of these results, we suggest testing different parametrization and thresholds until satisfactory kappa or other accuracy metrics values are achieved. Our results highlight the huge potential that MaxEnt has a as a tool for one-class classification, but a good understanding of the software settings and model parameterization is needed to obtain reliable results.

scholarly journals Improving Land Cover Classifications with Multiangular Data: MISR Data in Mainland Spain

2018 ◽  
Vol 10 (11) ◽  
pp. 1717
Author(s):  
Carlos Novillo ◽  
Patricia Arrogante-Funes ◽  
Raúl Romero-Calcerrada
Keyword(s):  
Land Cover ◽  
Spatial Resolution ◽  
Classification Accuracy ◽  
Land Cover Classification ◽  
Surface Anisotropy ◽  
Number Of Clusters ◽  
Directional Information ◽  
Land Covers ◽  
Effect Of Surface ◽  
Multiangle Imaging

In this study, we deal with the application of multiangular data from the Multiangle Imaging Spectroradiometer (MISR) sensor for studying the effect of surface anisotropy and directional information on the classification accuracy for different land covers with different rate of disaggregation classes (from four to 35 different classes) from a Mediterranean bioregion in Iberian, Spain. We used various MISR band groups from nadir to blue, green, red, and NIR channels at nadir and off-nadir. The MISR data utilized here were provided by the L1B2T product (275 m spatial resolution) and belonged to two different orbits. We performed 23 classifications with the k-means algorithm to test multiangular data, number of clusters, and iteration effects. Our findings confirmed that the multiangular information, in addition to the multispectral information used as the input of the k-means algorithm, improves the land cover classification accuracy, and this improvement increased with the level of disaggregation. A very large number of clusters produced even better improvements than multiangular data.

Texture-Based Land Cover Classification Algorithm Using Hidden Markov Model for Multispectral Data

2018 ◽  
pp. 579-613
Author(s):  
Jenicka S
Keyword(s):  
Land Cover ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Classification Accuracy ◽  
Hidden Markov ◽  
Land Cover Classification ◽  
Gray Level ◽  
Land Covers ◽  
Local Derivative ◽  
Local Derivative Pattern

In this chapter, the concept of stochastic optimal control is well explored using hidden Markov model (HMM) in classifying land covers of remotely sensed images. The features of land covers can be colour, shape, and texture. Texture is a useful feature in land cover classification. A texture-based land cover classification algorithm using HMM has been proposed. The local derivative pattern (LDP) texture descriptor for gray level images has been extended as multivariate local derivative pattern (MLDP) for remotely sensed images in this chapter. Experiments were conducted on IRS P6 LISS-IV data and the results were evaluated based on the classification accuracy and compared against the three existing methods such as wavelet, MLDP and colour gray level co-occurrence matrix (CGLCM). The results indicate that the proposed algorithm achieves a classification accuracy of 88.75%.

Very high resolution environmental predictors in species distribution models

2013 ◽  
Vol 38 (1) ◽  
pp. 79-96 ◽  
Author(s):  
Jean-Nicolas Pradervand ◽  
Anne Dubuis ◽  
Loïc Pellissier ◽  
Antoine Guisan ◽  
Christophe Randin
Keyword(s):  
High Resolution ◽  
Species Distribution ◽  
Species Distribution Models ◽  
Environmental Data ◽  
Swiss Alps ◽  
Fine Scale ◽  
Distribution Models ◽  
Model Quality ◽  
Vegetation Height ◽  
Very High

Recent advances in remote sensing technologies have facilitated the generation of very high resolution (VHR) environmental data. Exploratory studies suggested that, if used in species distribution models (SDMs), these data should enable modelling species’ micro-habitats and allow improving predictions for fine-scale biodiversity management. In the present study, we tested the influence, in SDMs, of predictors derived from a VHR digital elevation model (DEM) by comparing the predictive power of models for 239 plant species and their assemblages fitted at six different resolutions in the Swiss Alps. We also tested whether changes of the model quality for a species is related to its functional and ecological characteristics. Refining the resolution only contributed to slight improvement of the models for more than half of the examined species, with the best results obtained at 5 m, but no significant improvement was observed, on average, across all species. Contrary to our expectations, we could not consistently correlate the changes in model performance with species characteristics such as vegetation height. Temperature, the most important variable in the SDMs across the different resolutions, did not contribute any substantial improvement. Our results suggest that improving resolution of topographic data only is not sufficient to improve SDM predictions – and therefore local management – compared to previously used resolutions (here 25 and 100 m). More effort should be dedicated now to conduct finer-scale in-situ environmental measurements (e.g. for temperature, moisture, snow) to obtain improved environmental measurements for fine-scale species mapping and management.

Sugeno Fuzzy-Inference-System-Based Land Cover Classification of Remotely Sensed Images

2018 ◽  
pp. 326-363
Author(s):  
Jenicka S
Keyword(s):  
Land Cover ◽  
Fuzzy Inference ◽  
Land Cover Classification ◽  
Remotely Sensed ◽  
Inference System ◽  
Texture Model ◽  
Remotely Sensed Image ◽  
Land Covers ◽  
Remotely Sensed Images

Accuracy of land cover classification in remotely sensed images relies on the features extracted and the classifier used. Texture features are significant in land cover classification. Traditional texture models capture only patterns with discrete boundaries whereas fuzzy patterns need to be classified by assigning due weightage to uncertainty. When remotely sensed image contains noise, the image may have fuzzy patterns characterizing land covers and fuzzy boundaries separating land covers. So a fuzzy texture model is proposed for effective classification of land covers in remotely sensed images and the model uses Sugeno Fuzzy Inference System (FIS). Support Vector Machine (SVM) is used for precise and fast classification of image pixels. Hence it is proposed to use a hybrid of fuzzy texture model and SVM for land cover classification of remotely sensed images. In this chapter, land cover classification of IRS-P6, LISS-IV remotely sensed image is performed using multivariate version of the proposed texture model.

Sugeno Fuzzy-Inference-System-Based Land Cover Classification of Remotely Sensed Images

2019 ◽  
pp. 1247-1283
Author(s):  
Jenicka S.
Keyword(s):  
Land Cover ◽  
Fuzzy Inference ◽  
Land Cover Classification ◽  
Remotely Sensed ◽  
Inference System ◽  
Texture Model ◽  
Remotely Sensed Image ◽  
Land Covers ◽  
Remotely Sensed Images

Accuracy of land cover classification in remotely sensed images relies on the features extracted and the classifier used. Texture features are significant in land cover classification. Traditional texture models capture only patterns with discrete boundaries whereas fuzzy patterns need to be classified by assigning due weightage to uncertainty. When remotely sensed image contains noise, the image may have fuzzy patterns characterizing land covers and fuzzy boundaries separating land covers. So a fuzzy texture model is proposed for effective classification of land covers in remotely sensed images and the model uses Sugeno Fuzzy Inference System (FIS). Support Vector Machine (SVM) is used for precise and fast classification of image pixels. Hence it is proposed to use a hybrid of fuzzy texture model and SVM for land cover classification of remotely sensed images. In this chapter, land cover classification of IRS-P6, LISS-IV remotely sensed image is performed using multivariate version of the proposed texture model.

scholarly journals Automatic Classification of Major Urban Land Covers Based on Novel Spectral Indices

2018 ◽  
Vol 7 (12) ◽  
pp. 453 ◽  
Author(s):  
Mst Ilme Faridatul ◽  
Bo Wu
Keyword(s):  
Land Cover ◽  
Land Cover Classification ◽  
Urban Land ◽  
Support Vector ◽  
Landsat 8 ◽  
Spectral Indices ◽  
Urban Land Cover ◽  
Svm Algorithm ◽  
Bare Land ◽  
Land Covers

Urban land cover classification and mapping is an important and ongoing research field in monitoring and managing urban sprawl and terrestrial ecosystems. The changes in land cover largely affect the terrestrial ecosystem, thus information on land cover is important for understanding the ecological environment. Quantification of land cover in urban areas is challenging due to their diversified activities and large spatial and temporal variations. To improve urban land cover classification and mapping, this study presents three new spectral indices and an automated approach to classifying four major urban land types: impervious, bare land, vegetation, and water. A modified normalized difference bare-land index (MNDBI) is proposed to enhance the separation of impervious and bare land. A tasseled cap water and vegetation index (TCWVI) is proposed to enhance the detection of vegetation and water areas. A shadow index (ShDI) is proposed to further improve water detection by separating water from shadows. An approach for optimizing the thresholds of the new indices is also developed. Finally, the optimized thresholds are used to classify land covers using a decision tree algorithm. Using Landsat-8 Operational Land Imager (OLI) data from two study sites (Hong Kong and Dhaka City, Bangladesh) with different urban characteristics, the proposed approach is systematically evaluated. Spectral separability analysis of the new indices is performed and compared with other common indices. The urban land cover classifications achieved by the proposed approach are compared with those of the classic support vector machine (SVM) algorithm. The proposed approach achieves an overall classification accuracy of 94-96%, which is superior to the accuracy of the SVM algorithm.

scholarly journals Isolation Forests to Evaluate Class Separability and the Representativeness of Training and Validation Areas in Land Cover Classification

2019 ◽  
Vol 11 (24) ◽  
pp. 3000 ◽  
Author(s):  
Francisco Alonso-Sarria ◽  
Carmen Valdivieso-Ros ◽  
Francisco Gomariz-Castillo
Keyword(s):  
Remote Sensing ◽  
Random Forest ◽  
Land Cover ◽  
Classification Accuracy ◽  
Land Cover Classification ◽  
Landsat 8 ◽  
Commission Errors ◽  
Class Separability ◽  
Isolation Forest

Supervised land cover classification from remote sensing imagery is based on gathering a set of training areas to characterise each of the classes and to train a predictive model that is then used to predict land cover in the rest of the image. This procedure relies mainly on the assumptions of statistical separability of the classes and the representativeness of the training areas. This paper uses isolation forests, a type of random tree ensembles, to analyse both assumptions and to easily correct lack of representativeness by digitising new training areas where needed to improve the classification of a Landsat-8 set of images with Random Forest. The results show that the improved set of training areas after the isolation forest analysis is more representative of the whole image and increases classification accuracy. Besides, the distribution of isolation values can be useful to estimate class separability. A class separability parameter that summarises such distributions is proposed. This parameter is more correlated to omission and commission errors than other separability measures such as the Jeffries–Matusita distance.

scholarly journals Integrating Multitemporal Sentinel-1/2 Data for Coastal Land Cover Classification Using a Multibranch Convolutional Neural Network: A Case of the Yellow River Delta

2019 ◽  
Vol 11 (9) ◽  
pp. 1006 ◽  
Author(s):  
Quanlong Feng ◽  
Jianyu Yang ◽  
Dehai Zhu ◽  
Jiantao Liu ◽  
Hao Guo ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Deep Learning ◽  
Land Cover ◽  
Convolutional Neural Network ◽  
Classification Accuracy ◽  
Yellow River ◽  
Rapid Development ◽  
Land Cover Classification ◽  
Coastal Land

Coastal land cover classification is a significant yet challenging task in remote sensing because of the complex and fragmented nature of coastal landscapes. However, availability of multitemporal and multisensor remote sensing data provides opportunities to improve classification accuracy. Meanwhile, rapid development of deep learning has achieved astonishing results in computer vision tasks and has also been a popular topic in the field of remote sensing. Nevertheless, designing an effective and concise deep learning model for coastal land cover classification remains problematic. To tackle this issue, we propose a multibranch convolutional neural network (MBCNN) for the fusion of multitemporal and multisensor Sentinel data to improve coastal land cover classification accuracy. The proposed model leverages a series of deformable convolutional neural networks to extract representative features from a single-source dataset. Extracted features are aggregated through an adaptive feature fusion module to predict final land cover categories. Experimental results indicate that the proposed MBCNN shows good performance, with an overall accuracy of 93.78% and a Kappa coefficient of 0.9297. Inclusion of multitemporal data improves accuracy by an average of 6.85%, while multisensor data contributes to 3.24% of accuracy increase. Additionally, the featured fusion module in this study also increases accuracy by about 2% when compared with the feature-stacking method. Results demonstrate that the proposed method can effectively mine and fuse multitemporal and multisource Sentinel data, which improves coastal land cover classification accuracy.

Sign in / Sign up

Export Citation Format

Share Document