Search

Updated and accurate land cover maps are essential and crucial for sustainable crop production and efficient land management. However, accurate and efficient land cover mapping is still a challenge for agricultural regions with complicated landscapes. This study proposed a novel spectral-phenological based land cover classification (SPLC) method to identify the land cover for fragmented agricultural landscapes, with less requirement of ground truth data. The SPLC method integrated a pixel-based support vector machine (SVM) algorithm for cropland and various non-cropland classification, and a phenology-based automatic decision tree algorithm for identification of various crop types. It was then tested and applied in two typical case areas (i.e., Jiyuan in the upstream and Yonglian in the downstream) of Hetao Irrigation District (Hetao) in the upper Yellow River basin (YRB), northwest China. The field survey sampling data and the regional visual interpretation maps were jointly used to evaluate the accuracy of land cover classification. Results indicated that stable phenological rules can be established for crop identification even with complex planting patterns, and the SPLC method performed well in land cover mapping in case areas. Four high-accuracy land cover maps were produced for Jiyuan in 2020 and 2021, Yonglian in 2021, and Hetao in 2021. The overall accuracies (OA) can reach 0.90–0.94 based on evaluation with abundant ground truth data, and land cover maps agreed well with the visual interpretation maps in space. Overall, the case application validated the applicability and efficiency of the SPLC method in land cover mapping for regions with fragmented agricultural landscapes, and also implied the potential use in other similar regions. [ABSTRACT FROM AUTHOR]

Updated and accurate land cover maps are essential and crucial for sustainable crop production and efficient land management. However, accurate and efficient land cover mapping is still a challenge for agricultural regions with complicated landscapes. This study proposed a novel spectral-phenological based land cover classification (SPLC) method to identify the land cover for fragmented agricultural landscapes, with less requirement of ground truth data. The SPLC method integrated a pixel-based support vector machine (SVM) algorithm for cropland and various non-cropland classification, and a phenology-based automatic decision tree algorithm for identification of various crop types. It was then tested and applied in two typical case areas (i.e., Jiyuan in the upstream and Yonglian in the downstream) of Hetao Irrigation District (Hetao) in the upper Yellow River basin (YRB), northwest China. The field survey sampling data and the regional visual interpretation maps were jointly used to evaluate the accuracy of land cover classification. Results indicated that stable phenological rules can be established for crop identification even with complex planting patterns, and the SPLC method performed well in land cover mapping in case areas. Four high-accuracy land cover maps were produced for Jiyuan in 2020 and 2021, Yonglian in 2021, and Hetao in 2021. The overall accuracies (OA) can reach 0.90–0.94 based on evaluation with abundant ground truth data, and land cover maps agreed well with the visual interpretation maps in space. Overall, the case application validated the applicability and efficiency of the SPLC method in land cover mapping for regions with fragmented agricultural landscapes, and also implied the potential use in other similar regions.

Land cover classification is able to reflect the potential natural and social process in urban development, providing vital information to stakeholders. Recent solutions on land cover classification are generally addressed by remotely sensed imagery and supervised classification methods. However, a high-performance classifier is desirable but challenging due to the existence of model hyperparameters. Conventional approaches generally rely on manual tuning, which is time-consuming and far from satisfying. Therefore, this work aims to propose a systematic method to automatically tune the hyperparameters by Bayesian parameter optimization for the random forest classifier. The recently launched Sentinel-2A/B satellites are drawn to provide the remote sensing imageries for land cover classification case study in Beijing, China, which have the best spectral/spatial resolutions among the freely available satellites. The improved random forest with Bayesian parameter optimization is compared against the support vector machine (SVM) and random forest (RF) with default hyperparameters by discriminating five land cover classes including building, tree, road, water, and crop field. Comparative experimental results show that the optimized RF classifier outperforms the conventional SVM and the RF with default hyperparameters in terms of accuracy, precision, and recall. The effects of band/feature number and the band usefulness are also assessed. It is envisaged that the improved classifier for Sentinel-2 satellite image processing can find a wide range of applications where high-resolution satellite imagery classification is applicable. [ABSTRACT FROM AUTHOR]

Large-scale land cover classification from satellite imagery is still a challenge due to the big volume of data to be processed, to persistent cloud-cover in cloud-prone areas as well as seasonal artefacts that affect spatial homogeneity. Sentinel-2 times series from Copernicus Earth Observation program offer a great potential for fine scale land cover mapping thanks to high spatial and temporal resolutions, with a decametric resolution and five-day repeat time. However, the selection of best available scenes, their download together with the requirements in terms of storage and computing resources pose restrictions for large-scale land cover mapping. The dataset presented in this paper corresponds to global cloud-free pixel based composite created from the Sentinel-2 data archive (Level L1C) available in Google Earth Engine for the period January 2017- December 2018. The methodology used for generating the image composite is described and the metadata associated with the 10 m resolution dataset is presented. The data with a total volume of 15 TB is stored on the Big Data platform of the Joint Research Centre. It can be downloaded per UTM grid zone, loaded into GIS clients and displayed easily thanks to pre-computed overviews.

Land cover classification is able to reflect the potential natural and social process in urban development, providing vital information to stakeholders. Recent solutions on land cover classification are generally addressed by remotely sensed imagery and supervised classification methods. However, a high-performance classifier is desirable but challenging due to the existence of model hyperparameters. Conventional approaches generally rely on manual tuning, which is time-consuming and far from satisfying. Therefore, this work aims to propose a systematic method to automatically tune the hyperparameters by Bayesian parameter optimization for the random forest classifier. The recently launched Sentinel-2A/B satellites are drawn to provide the remote sensing imageries for land cover classification case study in Beijing, China, which have the best spectral/spatial resolutions among the freely available satellites. The improved random forest with Bayesian parameter optimization is compared against the support vector machine (SVM) and random forest (RF) with default hyperparameters by discriminating five land cover classes including building, tree, road, water, and crop field. Comparative experimental results show that the optimized RF classifier outperforms the conventional SVM and the RF with default hyperparameters in terms of accuracy, precision, and recall. The effects of band/feature number and the band usefulness are also assessed. It is envisaged that the improved classifier for Sentinel-2 satellite image processing can find a wide range of applications where high-resolution satellite imagery classification is applicable.