A number of national, regional and global land cover classification systems have been developed to meet specific user requirements for land cover mapping exercises, independent of scale, nomenclature and quality. However, this variety of land-cover classification systems limits the compatibility and comparability of land cover data. Furthermore, the current lack of interoperability between different land cover datasets, often stemming from incompatible land cover classification systems, makes analysis of multi-source, heterogeneous land cover data for various applications a very difficult task. This paper provides a critical review of the harmonization of land cover classification systems, which facilitates the generation, use and analysis of land cover maps consistently. Harmonization of existing land cover classification systems is essential to improve their cross-comparison and validation for understanding landscape patterns and changes. The paper reviews major land cover classification standards according to different scales, summarizes studies on harmonizing land cover mapping, and discusses some research problems that need to be solved and some future research directions.

土地利用/土地覆被变化是全球变化研究中的一个重要内容，而土地利用/土地覆被分类又是研究土地覆被变化的重要前提，它既影响着分类结果的表达，也决定着分类数据的应用领域。本文简要回顾和评述了国内外土地利用/土地覆被分类系统的研究进展。研究认为，土地利用/土地覆被分类系统，1970年代之前以土地利用分类为主，着重于土地用途的差异，主要用于土地利用现状调查和土地利用制图；1970年代随着遥感和计算机技术的发展，以土地覆被为主的分类系统迅速发展起来，它着重于土地类型的差异，主要用于土地覆被变化研究。研究指出，目前的土地利用/土地覆被分类系统一般都适用于特定研究目的和研究尺度，没有统一标准，这种土地分类系统的不兼容性，给土地覆被数据的汇总、分析与共享带来了诸多不便。但一个“万能”的土地分类系统又是不存在的。鉴于此，研究认为一个标准土地分类系统应该是多级的、开放的系统，高级别的土地覆被类型可以直接基于遥感影像进行识别，以便于实现分类数据的比较和共享；低级别的土地覆被类型可以根据特定研究目的灵活制定，以满足特定的研究需要。

Land use and land cover change (LUCC) is one of the most important aspects within the scope of global change. As a critical portion of LUCC study, classification of land use and land cover types not only affects the classification results, but also determines applications of relevant data. In the paper, studies of land use and land cover classification systems were reviewed. It could be concluded that the land use and land cover classification laid more emphasis on the land use classification before the 1970s. The land use classification system emphasized the differences between land functions and was mainly applied to land use inventory investigation and land use mapping. After then, the classification system based on land cover rapidly developed due to the development of satellite remote sensing and computer technology. This classification system emphasized the differences between land categories and was mainly applied to land cover change studies. The review shows that almost all current land use and land cover classification systems tend to be suitable only for a specific research purpose at a certain scale. The incompatibility amongst the current classification systems has resulted in numerous inconveniences and difficulties in the courses of aggregation, analysis, and sharing of land use and land cover data due to the absence of consistent standards. Therefore, a standardized classification system is extremely warranted. However, a universal classification system suitable for all kinds of research purposes is neither possible nor necessary. The reasons lie in that on the one hand, the minimum classification unit could be dependent on the mapping scale as well as the spatial resolution of remote sensing data; on the other hand, land use and land cover types of varying detailed degrees are required for different research purposes. Furthermore, it would be probable that some special land use and land cover types existed in specific regions, for example, the Qinghai-Tibet Plateau in China. At last, this review states that a standardized classification system should be hierarchically organized and could be extended. The land use and land cover types of higher hierarchy could be directly identified from remote sensing images without auxiliary information, which would make it convenient for data comparison and sharing. The land use and land cover types of lower hierarchy could be defined in terms of a specific study purpose, which could satisfy the specific study needs.

Accurate and reliable information on the spatial distribution of major crops is needed for detecting possible production deficits with the aim of preventing food security crises and anticipating response planning. In this paper, we compared some of the most widely used global land cover datasets to examine their comparative advantages for cropland monitoring. Cropland class areas are compared for the following datasets: FAO-GLCshare (FAO Global Land Cover Network), Geowiki IIASA-Hybrid (Hybrid global land cover map from the International Institute of Applied System Analysis), GLC2000 (Global Land Cover 2000), GLCNMO2008 (Global Land Cover by National Mapping Organizations), GlobCover, Globeland30, LC-CCI (Land Cover Climate Change Initiative) 2010 and 2015, and MODISLC (MODIS Land Cover product). The methodology involves: (1) highlighting discrepancies in the extent and spatial distribution of cropland, (2) comparing the areas with FAO agricultural statistics at the country level, and (3) providing accuracy assessment through freely available reference datasets. Recommendations for crop monitoring at the country level are based on a priority ranking derived from the results obtained from analyses 2 and 3. Our results revealed that cropland information varies substantially among the analyzed land cover datasets. FAO-GLCshare and Globeland30 generally provided adequate results to monitor cropland areas, whereas LC-CCI2010 and GLC2000 are less unsuitable due to large overestimations in the former and out of date information and low accuracy in the latter. The recently launched LC-CCI datasets (i.e., LC-CCI2015) show a higher potential for cropland monitoring uses than the previous version (i.e., LC-CCI2010).

. Improving systematic observations of land cover, as an Essential Climate Variable, should contribute to a better understanding of the global climate system and thus improve our ability to predict climatic change. The aim of this paper is to bring global land cover observations closer to meeting the needs of climate science. First, consultation mechanisms were established with the climate modeling community to identify its specific requirements in terms of satellite-based global land cover products. This assessment highlighted specific needs in terms of land cover characterization, accuracy of products, as well as stability and consistency needs that are currently not met or even addressed. The current land cover representation and mapping techniques were then called into question to specifically focus on the critical need of stable products expressed by climate users. Decoupling the stable and dynamic components of the land cover characterization and using a multi-year dataset were proposed as two key approaches to allow generating consistent suites of global land cover products over time.

Over past decades, a lot of global land-cover products have been released; however, these still lack a global land-cover map with a fine classification system and spatial resolution simultaneously. In this study, a novel global 30m land-cover classification with a fine classification system for the year 2015 (GLC_FCS30-2015) was produced by combining time series of Landsat imagery and high-quality training data from the GSPECLib (Global Spatial Temporal Spectra Library) on the Google Earth Engine computing platform. First, the global training data from the GSPECLib were developed by applying a series of rigorous filters to the CCI_LC (Climate Change Initiative Global Land Cover) land-cover and MCD43A4 NBAR products (MODIS Nadir Bidirectional Reflectance Distribution Function-Adjusted Reflectance). Secondly, a local adaptive random forest model was built for each 5 degrees x 5 degrees geographical tile by using the multi-temporal Landsat spectral and texture features and the corresponding training data, and the GLC_FCS30-2015 land-cover product containing 30 land-cover types was generated for each tile. Lastly, the GLC_FCS30-2015 was validated using three different validation systems (containing different land-cover details) using 44 043 validation samples. The validation results indicated that the GLC_FCS30-2015 achieved an overall accuracy of 82.5% and a kappa coefficient of 0.784 for the level-0 validation system (9 basic land-cover types), an overall accuracy of 71.4% and kappa coefficient of 0.686 for the UN-LCCS (United Nations Land Cover Classification System) level1 system (16 LCCS land-cover types), and an overall accuracy of 68.7% and kappa coefficient of 0.662 for the UN-LCCS level-2 system (24 fine land-cover types). The comparisons against other land-cover products (CCI_LC, MCD12Q1, FROM_GLC, and GlobeLand30) indicated that GLC_FCS30-2015 provides more spatial details than CCI_LC-2015 and MCD12Q1-2015 and a greater diversity of land-cover types than FROM_GLC-2015 and GlobeLand30-2010. They also showed that GLC_FCS30-2015 achieved the best overall accuracy of 82.5% against FROM_GLC-2015 of 59.1% and GlobeLand30-2010 of 75.9 %. Therefore, it is concluded that the GLC_FCS30-2015 product is the first global land-cover dataset that provides a fine classification system (containing 16 global LCCS land-cover types as well as 14 detailed and regional land-cover types) with high classification accuracy at 30 m. The GLC_FCS30-2015 global land-cover products produced in this paper are free access at https://doi.org/10.5281/zenodo.3986872 (Liu et al., 2020).

Global land cover is one of the essential terrestrial baseline datasets available for ecosystem modeling, however uncertainty remains an issue. Tools such as Google Earth offer enormous potential for land cover validation. With an ever increasing amount of very fine spatial resolution images (up to 50 cm × 50 cm) available on Google Earth, it is becoming possible for every Internet user (including non remote sensing experts) to distinguish land cover features with a high degree of reliability. Such an approach is inexpensive and allows Internet users from any region of the world to get involved in this global validation exercise. The Geo-Wiki Project is a global network of volunteers who wish to help improve the quality of global land cover maps. Since large differences occur between existing global land cover maps, current ecosystem and land-use science lacks crucial accurate data (e.g., to determine the potential of additional agricultural land available to grow crops in Africa), volunteers are asked to review hotspot maps of global land cover disagreement and determine, based on what they actually see in Google Earth and their local knowledge, if the land cover maps are correct or incorrect. Their input is recorded in a database, along with uploaded photos, to be used in the future for the creation of a new and improved hybrid global land cover map.

. Land cover is the physical material at the surface of the Earth. As the cause and result of global environmental change, land cover\nchange (LCC) influences the global energy balance and biogeochemical cycles.\nContinuous and dynamic monitoring of global LC is urgently needed. Effective\nmonitoring and comprehensive analysis of LCC at the global scale are rare.\nWith the latest version of GLASS (Global Land Surface Satellite) CDRs\n(climate data records) from 1982 to 2015, we built the first record of\n34-year-long annual dynamics of global land cover (GLASS-GLC) at 5 km\nresolution using the Google Earth Engine (GEE) platform. Compared to earlier\nglobal land cover (LC) products, GLASS-GLC is characterized by high consistency, more\ndetail, and longer temporal coverage. The average overall accuracy for the\n34 years each with seven classes, including cropland, forest, grassland,\nshrubland, tundra, barren land, and snow/ice, is 82.81 % based on 2431\ntest sample units. We implemented a systematic uncertainty analysis and\ncarried out a comprehensive spatiotemporal pattern analysis. Significant\nchanges at various scales were found, including barren land loss and\ncropland gain in the tropics, forest gain in the Northern Hemisphere, and\ngrassland loss in Asia. A global quantitative analysis of human factors\nshowed that the average human impact level in areas with significant LCC was\nabout 25.49 %. The anthropogenic influence has a strong correlation with\nthe noticeable vegetation gain, especially for forest. Based on GLASS-GLC,\nwe can conduct long-term LCC analysis, improve our understanding of global\nenvironmental change, and mitigate its negative impact. GLASS-GLC will be\nfurther applied in Earth system modeling to facilitate research on global\ncarbon and water cycling, vegetation dynamics, and climate change. The\nGLASS-GLC data set presented in this article is available at\nhttps://doi.org/10.1594/PANGAEA.913496 (Liu et al., 2020).

Substantial progress has been made in the field of large-area land cover mapping as the spatial resolution of remotely sensed data increases. However, a significant amount of human power is still required to label images for training and testing purposes, especially in high-resolution (e.g., 3-m) land cover mapping. In this research, we propose a solution that can produce 3-m resolution land cover maps on a national scale without human efforts being involved. First, using the public 10-m resolution land cover maps as an imperfect training dataset, we propose a deep learning based approach that can effectively transfer the existing knowledge. Then, we improve the efficiency of our method through a network pruning process for national-scale land cover mapping. Our proposed method can take the state-of-the-art 10-m resolution land cover maps (with an accuracy of 81.24% for China) as the training data, enable a transferred learning process that can produce 3-m resolution land cover maps, and further improve the overall accuracy (OA) to 86.34% for China. We present detailed results obtained over three mega cities in China, to demonstrate the effectiveness of our proposed approach for 3-m resolution large-area land cover mapping.

. In China, the demand for a more precise perception of the national land surface has become most urgent given the pace of development and urbanization. Constructing a very-high-resolution (VHR) land-cover dataset for China with national coverage, however, is a nontrivial task. Thus, this has become an active area of research that is impeded by the challenges of image acquisition, manual annotation, and computational complexity. To fill this gap, the first 1 m resolution national-scale land-cover map of China, SinoLC-1, was established using a deep-learning-based framework and open-access data, including global land-cover (GLC) products, OpenStreetMap (OSM), and Google Earth imagery. Reliable training labels were generated by combining three 10 m GLC products and OSM data. These training labels and 1 m resolution images derived from Google Earth were used to train the proposed framework. This framework resolved the label noise stemming from a resolution mismatch between images and labels by combining a resolution-preserving backbone, a weakly supervised module, and a self-supervised loss function, to refine the VHR land-cover results automatically without any manual annotation requirement. Based on large-storage and computing servers, processing the 73.25 TB dataset to obtain the SinoLC-1 covering the entirety of China, ∼ 9 600 000 km2, took about 10 months. The SinoLC-1 product was validated using a visually interpreted validation set including over 100 000 random samples and a statistical validation set collected from the official land survey report provided by the Chinese government. The validation results showed that SinoLC-1 achieved an overall accuracy of 73.61 % and a κ coefficient of 0.6595. Validations for every provincial region further indicated the accuracy of this dataset across the whole of China. Furthermore, the statistical validation results indicated that SinoLC-1 conformed to the official survey reports with an overall misestimation rate of 6.4 %. In addition, SinoLC-1 was compared with five other widely used GLC products. These results indicated that SinoLC-1 had the highest spatial resolution and the finest landscape details. In conclusion, as the first 1 m resolution national-scale land-cover map of China, SinoLC-1 delivered accuracy and provided primal support for related research and applications throughout China. The SinoLC-1 land-cover product is freely accessible at https://doi.org/10.5281/zenodo.7707461 (Li et al., 2023).

. Urban green space (UGS) is an important component in the urban ecosystem and has great significance to the urban ecological environment. Although the development of remote sensing platforms and deep learning technologies have provided opportunities for UGS mapping from high-resolution images (HRIs), challenges still exist in its large-scale and fine-grained application due to insufficient annotated datasets and specially designed methods for UGS. Moreover, the domain shift between images from different regions is also a problem that must be solved. To address these issues, a general deep learning (DL) framework is proposed for UGS mapping in the large scale, and fine-grained UGS maps of 31 major cities in mainland China are generated (UGS-1m). The DL framework consists of a generator and a discriminator. The generator is a fully convolutional network designed for UGS extraction (UGSNet), which integrates attention mechanisms to improve the discrimination to UGS, and employs a point-rending strategy for edge recovery. The discriminator is a fully connected network aiming to deal with the domain shift between images. To support the model training, an urban green space dataset (UGSet) with a total number of 4544 samples of 512×512 in size is provided. The main steps to obtain UGS-1m can be summarized as follows: (a) first, the UGSNet will be pre-trained on the UGSet in order to obtain a good starting training point for the generator. (b) After pre-training on the UGSet, the discriminator is responsible for adapting the pre-trained UGSNet to different cities through adversarial training. (c) Finally, the UGS results of 31 major cities in China (UGS-1m) are obtained using 2179 Google Earth images with a data frame of 7′30′′ in longitude and 5′00′′ in latitude and a spatial resolution of nearly 1.1 m. An evaluation of the performance of the proposed framework by samples from five different cities shows the validity of the UGS-1m products, with an average overall accuracy (OA) of 87.56 % and an F1 score of 74.86 %. Comparative experiments on UGSet with the existing state-of-the-art (SOTA) DL models proves the effectiveness of UGSNet as the generator, with the highest F1 score of 77.30 %. Furthermore, an ablation study on the discriminator fully reveals the necessity and effectiveness of introducing the discriminator into adversarial learning for domain adaptation. Finally, a comparison with existing products further shows the feasibility of the UGS-1m and the great potential of the proposed DL framework. The UGS-1m can be downloaded from https://doi.org/10.57760/sciencedb.07049 (Shi et al., 2023).