Aerospace Information Research Institute

Convolutional neural networks (CNNs) have been attracting increasing attention in hyperspectral (HS) image classification due to their ability to capture spatial-spectral feature representations. Nevertheless, their ability in modeling relations between the samples remains limited. Beyond the limitations of grid sampling, graph convolutional networks (GCNs) have been recently proposed and successfully applied in irregular (or nongrid) data representation and analysis. In this article, we thoroughly investigate CNNs and GCNs (qualitatively and quantitatively) in terms of HS image classification. Due to the construction of the adjacency matrix on all the data, traditional GCNs usually suffer from a huge computational cost, particularly in large-scale remote sensing (RS) problems. To this end, we develop a new minibatch GCN (called miniGCN hereinafter), which allows to train large-scale GCNs in a minibatch fashion. More significantly, our miniGCN is capable of inferring out-of-sample data without retraining networks and improving classification performance. Furthermore, as CNNs and GCNs can extract different types of HS features, an intuitive solution to break the performance bottleneck of a single model is to fuse them. Since miniGCNs can perform batchwise network training (enabling the combination of CNNs and GCNs), we explore three fusion strategies: additive fusion, elementwise multiplicative fusion, and concatenation fusion to measure the obtained performance gain. Extensive experiments, conducted on three HS data sets, demonstrate the advantages of miniGCNs over GCNs and the superiority of the tested fusion strategies with regard to the single CNN or GCN models. The codes of this work will be available at https://github.com/danfenghong/IEEE_TGRS_GCN for the sake of reproducibility.

Y Artificial intelligence (AI) coupled with promising machine learning (ML) techniques well known from computer science is broadly affecting many aspects of various fields including science and technology, industry, and even our day-to-day life. The ML techniques have been developed to analyze high-throughput data with a view to obtaining useful insights, categorizing, predicting, and making evidence-based decisions in novel ways, which will promote the growth of novel applications and fuel the sustainable booming of AI. This paper undertakes a comprehensive survey on the development and application of AI in different aspects of fundamental sciences, including information science, mathematics, medical science, materials science, geoscience, life science, physics, and chemistry. The challenges that each discipline of science meets, and the potentials of AI techniques to handle these challenges, are discussed in detail. Moreover, we shed light on new research trends entailing the integration of AI into each scientific discipline. The aim of this paper is to provide a broad research guideline on fundamental sciences with potential infusion of AI, to help motivate researchers to deeply understand the state-of-the-art applications of AI-based fundamental sciences, and thereby to help promote the continuous development of these fundamental sciences.

Classification and identification of the materials lying over or beneath the earth's surface have long been a fundamental but challenging research topic in geoscience and remote sensing (RS), and have garnered a growing concern owing to the recent advancements of deep learning techniques. Although deep networks have been successfully applied in single-modality-dominated classification tasks, yet their performance inevitably meets the bottleneck in complex scenes that need to be finely classified, due to the limitation of information diversity. In this work, we provide a baseline solution to the aforementioned difficulty by developing a general multimodal deep learning (MDL) framework. In particular, we also investigate a special case of multi-modality learning (MML)-cross-modality learning (CML) that exists widely in RS image classification applications. By focusing on “what,” “where,” and “how” to fuse, we show different fusion strategies as well as how to train deep networks and build the network architecture. Specifically, five fusion architectures are introduced and developed, further being unified in our MDL framework. More significantly, our framework is not only limited to pixel-wise classification tasks but also applicable to spatial information modeling with convolutional neural networks (CNNs). To validate the effectiveness and superiority of the MDL framework, extensive experiments related to the settings of MML and CML are conducted on two different multimodal RS data sets. Furthermore, the codes and data sets will be available at https://github.com/danfenghong/IEEE_TGRS_MDL-RS, contributing to the RS community.

Global development has been heavily reliant on the overexploitation of natural resources since the Industrial Revolution. With the extensive use of fossil fuels, deforestation, and other forms of land-use change, anthropogenic activities have contributed to the ever-increasing concentrations of greenhouse gases (GHGs) in the atmosphere, causing global climate change. In response to the worsening global climate change, achieving carbon neutrality by 2050 is the most pressing task on the planet. To this end, it is of utmost importance and a significant challenge to reform the current production systems to reduce GHG emissions and promote the capture of CO2 from the atmosphere. Herein, we review innovative technologies that offer solutions achieving carbon (C) neutrality and sustainable development, including those for renewable energy production, food system transformation, waste valorization, C sink conservation, and C-negative manufacturing. The wealth of knowledge disseminated in this review could inspire the global community and drive the further development of innovative technologies to mitigate climate change and sustainably support human activities.

Abstract. 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 30 m 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∘×5∘ 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) level-1 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).

Learning-based infrared small object detection methods currently rely heavily on the classification backbone network. This tends to result in tiny object loss and feature distinguishability limitations as the network depth increases. Furthermore, small objects in infrared images are frequently emerged bright and dark, posing severe demands for obtaining precise object contrast information. For this reason, we in this paper propose a simple and effective "U-Net in U-Net" framework, UIU-Net for short, and detect small objects in infrared images. As the name suggests, UIU-Net embeds a tiny U-Net into a larger U-Net backbone, enabling the multi-level and multi-scale representation learning of objects. Moreover, UIU-Net can be trained from scratch, and the learned features can enhance global and local contrast information effectively. More specifically, the UIU-Net model is divided into two modules: the resolution-maintenance deep supervision (RM-DS) module and the interactive-cross attention (IC-A) module. RM-DS integrates Residual U-blocks into a deep supervision network to generate deep multi-scale resolution-maintenance features while learning global context information. Further, IC-A encodes the local context information between the low-level details and high-level semantic features. Extensive experiments conducted on two infrared single-frame image datasets, i.e., SIRST and Synthetic datasets, show the effectiveness and superiority of the proposed UIU-Net in comparison with several state-of-the-art infrared small object detection methods. The proposed UIU-Net also produces powerful generalization performance for video sequence infrared small object datasets, e.g., ATR ground/air video sequence dataset. The codes of this work are available openly at https://github.com/danfenghong/IEEE.

The foundation model has recently garnered significant attention due to its potential to revolutionize the field of visual representation learning in a self-supervised manner. While most foundation models are tailored to effectively process RGB images for various visual tasks, there is a noticeable gap in research focused on spectral data, which offers valuable information for scene understanding, especially in remote sensing (RS) applications. To fill this gap, we created for the first time a universal RS foundation model, named SpectralGPT, which is purpose-built to handle spectral RS images using a novel 3D generative pretrained transformer (GPT). Compared to existing foundation models, SpectralGPT 1) accommodates input images with varying sizes, resolutions, time series, and regions in a progressive training fashion, enabling full utilization of extensive RS Big Data; 2) leverages 3D token generation for spatial-spectral coupling; 3) captures spectrally sequential patterns via multi-target reconstruction; and 4) trains on one million spectral RS images, yielding models with over 600 million parameters. Our evaluation highlights significant performance improvements with pretrained SpectralGPT models, signifying substantial potential in advancing spectral RS Big Data applications within the field of geoscience across four downstream tasks: single/multi-label scene classification, semantic segmentation, and change detection.

Flexible wearable sweat sensors allow continuous, real-time, noninvasive detection of sweat analytes, provide insight into human physiology at the molecular level, and have received significant attention for their promising applications in personalized health monitoring. Electrochemical sensors are the best choice for wearable sweat sensors due to their high performance, low cost, miniaturization, and wide applicability. Recent developments in soft microfluidics, multiplexed biosensing, energy harvesting devices, and materials have advanced the compatibility of wearable electrochemical sweat-sensing platforms. In this review, we summarize the potential of sweat for medical detection and methods for sweat stimulation and collection. This paper provides an overview of the components of wearable sweat sensors and recent developments in materials and power supply technologies and highlights some typical sensing platforms for different types of analytes. Finally, the paper ends with a discussion of the challenges and a view of the prospective development of this exciting field.

SAR Ship Detection Dataset (SSDD) is the first open dataset that is widely used to research state-of-the-art technology of ship detection from Synthetic Aperture Radar (SAR) imagery based on deep learning (DL). According to our investigation, up to 46.59% of the total 161 public reports confidently select SSDD to study DL-based SAR ship detection. Undoubtedly, this situation reveals the popularity and great influence of SSDD in the SAR remote sensing community. Nevertheless, the coarse annotations and ambiguous standards of use of its initial version both hinder fair methodological comparisons and effective academic exchanges. Additionally, its single-function horizontal-vertical rectangle bounding box (BBox) labels can no longer satisfy the current research needs of the rotatable bounding box (RBox) task and the pixel-level polygon segmentation task. Therefore, to address the above two dilemmas, in this review, advocated by the publisher of SSDD, we will make an official release of SSDD based on its initial version. SSDD’s official release version will cover three types: (1) a bounding box SSDD (BBox-SSDD), (2) a rotatable bounding box SSDD (RBox-SSDD), and (3) a polygon segmentation SSDD (PSeg-SSDD). We relabel ships in SSDD more carefully and finely, and then explicitly formulate some strict using standards, e.g., (1) the training-test division determination, (2) the inshore-offshore protocol, (3) the ship-size reasonable definition, (4) the determination of the densely distributed small ship samples, and (5) the determination of the densely parallel berthing at ports ship samples. These using standards are all formulated objectively based on the using differences of existing 75 (161 × 46.59%) public reports. They will be beneficial for fair method comparison and effective academic exchanges in the future. Most notably, we conduct a comprehensive data analysis on BBox-SSDD, RBox-SSDD, and PSeg-SSDD. Our analysis results can provide some valuable suggestions for possible future scholars to further elaborately design DL-based SAR ship detectors with higher accuracy and stronger robustness when using SSDD.

With the extremely rapid advances in remote sensing (RS) technology, a great quantity of Earth observation (EO) data featuring considerable and complicated heterogeneity are readily available nowadays, which renders researchers an opportunity to tackle current geoscience applications in a fresh way. With the joint utilization of EO data, much research on multimodal RS data fusion has made tremendous progress in recent years, yet these developed traditional algorithms inevitably meet the performance bottleneck due to the lack of the ability to comprehensively analyze and interpret strongly heterogeneous data. Hence, this non-negligible limitation further arouses an intense demand for an alternative tool with powerful processing competence. Deep learning (DL), as a cutting-edge technology, has witnessed remarkable breakthroughs in numerous computer vision tasks owing to its impressive ability in data representation and reconstruction. Naturally, it has been successfully applied to the field of multimodal RS data fusion, yielding great improvement compared with traditional methods. This survey aims to present a systematic overview in DL-based multimodal RS data fusion. More specifically, some essential knowledge about this topic is first given. Subsequently, a literature survey is conducted to analyze the trends of this field. Some prevalent sub-fields in the multimodal RS data fusion are then reviewed in terms of the to-be-fused data modalities, i.e., spatiospectral, spatiotemporal, light detection and ranging-optical, synthetic aperture radar-optical, and RS-Geospatial Big Data fusion. Furthermore, We collect and summarize some valuable resources for the sake of the development in multimodal RS data fusion. Finally, the remaining challenges and potential future directions are highlighted.

Hyperspectral anomaly detection (HAD) aims to identify anomalous targets that deviate from the surrounding background in unlabeled hyperspectral images (HSIs). Most existing deep networks that exploit reconstruction errors to detect anomalies are prone to fit anomalous pixels, thus yielding small reconstruction errors for anomalies, which is not favorable for separating targets from HSIs. In order to achieve a superior background reconstruction network for HAD purposes, this paper proposes a self-supervised blind-block network (termed BockNet) with a guard window. BockNet creates a blind-block (guard window) in the center of the network’s receptive field, rendering it unable to see the information inside the guard window when reconstructing the central pixel. This process seamlessly embeds a sliding dual-window model into our BockNet, in which the inner window is the guard window and the outer window is the receptive field outside the guard window. Naturally, BockNet utilizes only the outer window information to predict/reconstruct the central pixel of the perceptive field. During the reconstruction of pixels inside anomalous targets of varying sizes, the targets typically fall into the guard window, weakening the contribution of anomalies to the reconstruction results so that those reconstructed pixels converge to the background distribution of the outer window area. Accordingly, the reconstructed HSI can be deemed as a pure background HSI, and the reconstruction error of anomalous pixels will be further enlarged, thus improving the discrimination ability of the BockNet model for anomalies. Extensive experiments on four datasets illustrate the competitive and satisfactory performance of our BockNet compared to other state-of-the-art detectors.

Artificial intelligence (AI) approaches nowadays have gained remarkable success in single-modality-dominated remote sensing (RS) applications, especially with an emphasis on individual urban environments (e.g., single cities or regions). Yet these AI models tend to meet the performance bottleneck in the case studies across cities or regions, due to the lack of diverse RS information and cutting-edge solutions with high generalization ability. To this end, we build a new set of multimodal remote sensing benchmark datasets (including hyperspectral, multispectral, SAR) for the study purpose of the cross-city semantic segmentation task (called C2Seg dataset), which consists of two cross-city scenes, i.e., Berlin-Augsburg (in Germany) and Beijing-Wuhan (in China). Beyond the single city, we propose a high -resolution d omain a daptation n etwork, HighDAN for short, to promote the AI model's generalization ability from the multi-city environments. HighDAN is capable of retaining the spatially topological structure of the studied urban scene well in a parallel high-to-low resolution fusion fashion but also closing the gap derived from enormous differences of RS image representations between different cities by means of adversarial learning. In addition, the Dice loss is considered in HighDAN to alleviate the class imbalance issue caused by factors across cities. Extensive experiments conducted on the C2Seg dataset show the superiority of our HighDAN in terms of segmentation performance and generalization ability, compared to state-of-the-art competitors. The C2Seg dataset and the semantic segmentation toolbox (involving the proposed HighDAN) will be available publicly at https://github.com/danfenghong/RSE_Cross-city . • A new multimodal remote sensing benchmark for cross-city semantic segmentation. • Propose a high-resolution domain adaptation network for semantic segmentation. • Balance spatial topology, domain gaps, eases city class imbalance with Dice loss.

Vision transformers (ViTs) have been trending in image classification tasks due to their promising performance when compared to convolutional neural networks (CNNs). As a result, many researchers have tried to incorporate ViTs in hyperspectral image (HSI) classification tasks. To achieve satisfactory performance, close to that of CNNs, transformers need fewer parameters. ViTs and other similar transformers use an external classification (CLS) token which is randomly initialized and often fails to generalize well, whereas other sources of multimodal datasets, such as light detection and ranging (LiDAR) offer the potential to improve these models by means of a CLS. In this paper, we introduce a new multimodal fusion transformer (MFT) network which comprises a multihead cross patch attention (mCrossPA) for HSI land-cover classification. Our mCrossPA utilizes other sources of complementary information in addition to the HSI in the transformer encoder to achieve better generalization. The concept of tokenization is used to generate CLS and HSI patch tokens, helping to learn a distinctive representation in a reduced and hierarchical feature space. Extensive experiments are carried out on widely used benchmark datasets i.e., the University of Houston, Trento, University of Southern Mississippi Gulfpark (MUUFL), and Augsburg. We compare the results of the proposed MFT model with other state-of-the-art transformers, classical CNNs, and conventional classifiers models. The superior performance achieved by the proposed model is due to the use of multihead cross patch attention. The source code will be made available publicly at https://github.com/AnkurDeria/MFT.

Due to advances in remote sensing satellite imaging and image processing technologies and their wide applications, intelligent remote sensing satellites are facing an opportunity for rapid development. The key technologies, standards, and laws of intelligent remote sensing satellites are also experiencing a series of new challenges. Novel concepts and key technologies in the intelligent hyperspectral remote sensing satellite system have been proposed since 2011. The aim of these intelligent remote sensing satellites is to provide real-time, accurate, and personalized remote sensing information services. This article reviews the current developments in new-generation intelligent remote sensing satellite systems, with a focus on intelligent remote sensing satellite platforms, imaging payloads, onboard processing systems, and other key technological chains. The technological breakthroughs and current defects of intelligence-oriented designs are also analyzed. Intelligent remote sensing satellites collect personalized remote sensing data and information, with real-time data features and information interaction between remote sensing satellites or between satellites and the ground. Such developments will expand the use of remote sensing applications beyond government departments and industrial users to a massive number of individual users. However, this extension faces challenges regarding privacy protection, societal values, and laws regarding the sharing and distribution of data and information.

Hyperspectral imaging (HSI) has been extensively utilized in many real-life applications because it benefits from the detailed spectral information contained in each pixel. Notably, the complex characteristics, i.e., the nonlinear relation among the captured spectral information and the corresponding object of HSI data, make accurate classification challenging for traditional methods. In the last few years, deep learning (DL) has been substantiated as a powerful feature extractor that effectively addresses the nonlinear problems that appeared in a number of computer vision tasks. This prompts the deployment of DL for HSI classification (HSIC) which revealed good performance. This survey enlists a systematic overview of DL for HSIC and compared state-of-the-art strategies of the said topic. Primarily, we will encapsulate the main challenges of TML for HSIC and then we will acquaint the superiority of DL to address these problems. This article breaks down the state-of-the-art DL frameworks into spectral-features, spatial-features, and together spatial–spectral features to systematically analyze the achievements (future research directions as well) of these frameworks for HSIC. Moreover, we will consider the fact that DL requires a large number of labeled training examples whereas acquiring such a number for HSIC is challenging in terms of time and cost. Therefore, this survey discusses some strategies to improve the generalization performance of DL strategies which can provide some future guidelines.

Abstract. Satellite-based models have been widely used to simulate vegetation gross primary production (GPP) at the site, regional, or global scales in recent years. However, accurately reproducing the interannual variations in GPP remains a major challenge, and the long-term changes in GPP remain highly uncertain. In this study, we generated a long-term global GPP dataset at 0.05∘ latitude by 0.05∘ longitude and 8 d interval by revising a light use efficiency model (i.e., EC-LUE model). In the revised EC-LUE model, we integrated the regulations of several major environmental variables: atmospheric CO2 concentration, radiation components, and atmospheric vapor pressure deficit (VPD). These environmental variables showed substantial long-term changes, which could greatly impact the global vegetation productivity. Eddy covariance (EC) measurements at 95 towers from the FLUXNET2015 dataset, covering nine major ecosystem types around the globe, were used to calibrate and validate the model. In general, the revised EC-LUE model could effectively reproduce the spatial, seasonal, and annual variations in the tower-estimated GPP at most sites. The revised EC-LUE model could explain 71 % of the spatial variations in annual GPP over 95 sites. At more than 95 % of the sites, the correlation coefficients (R2) of seasonal changes between tower-estimated and model-simulated GPP are larger than 0.5. Particularly, the revised EC-LUE model improved the model performance in reproducing the interannual variations in GPP, and the averaged R2 between annual mean tower-estimated and model-simulated GPP is 0.44 over all 55 sites with observations longer than 5 years, which is significantly higher than those of the original EC-LUE model (R2=0.36) and other LUE models (R2 ranged from 0.06 to 0.30 with an average value of 0.16). At the global scale, GPP derived from light use efficiency models, machine learning models, and process-based biophysical models shows substantial differences in magnitude and interannual variations. The revised EC-LUE model quantified the mean global GPP from 1982 to 2017 as 106.2±2.9 Pg C yr−1 with the trend 0.15 Pg C yr−1. Sensitivity analysis indicated that GPP simulated by the revised EC-LUE model was sensitive to atmospheric CO2 concentration, VPD, and radiation. Over the period of 1982–2017, the CO2 fertilization effect on the global GPP (0.22±0.07 Pg C yr−1) could be partly offset by increased VPD (-0.17±0.06 Pg C yr−1). The long-term changes in the environmental variables could be well reflected in global GPP. Overall, the revised EC-LUE model is able to provide a reliable long-term estimate of global GPP. The GPP dataset is available at https://doi.org/10.6084/m9.figshare.8942336.v3 (Zheng et al., 2019).

In recent years, enormous research has been made to improve the classification performance of single-modal remote sensing (RS) data. However, with the ever-growing availability of RS data acquired from satellite or airborne platforms, simultaneous processing and analysis of multimodal RS data pose a new challenge to researchers in the RS community. To this end, we propose a deep-learning-based new framework for multimodal RS data classification, where convolutional neural networks (CNNs) are taken as a backbone with an advanced cross-channel reconstruction module, called CCR-Net. As the name suggests, CCR-Net learns more compact fusion representations of different RS data sources by the means of the reconstruction strategy across modalities that can mutually exchange information in a more effective way. Extensive experiments conducted on two multimodal RS datasets, including hyperspectral (HS) and light detection and ranging (LiDAR) data, i.e., the Houston2013 dataset, and HS and synthetic aperture radar (SAR) data, i.e., the Berlin dataset, demonstrate the effectiveness and superiority of the proposed CCR-Net in comparison with several state-of-the-art multimodal RS data classification methods. The codes will be openly and freely available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/danfenghong/IEEE_TGRS_CCR-Net</uri> for the sake of reproducibility.

Metal halide perovskites have aroused burgeoning interest in the field of photovoltaics owing to their versatile optoelectronic properties. The outstanding power conversion efficiency, high specific power (i.e., power to weight ratio), compatibility with flexible substrates, and excellent radiation resistance of perovskite solar cells (PSCs) enable them to be a promising candidate for next-generation space photovoltaic technology. Nevertheless, compared with other practical space photovoltaics, such as silicon and III-V multi-junction compound solar cells, the research on PSCs for space applications is just in the infancy stage. Therefore, there are considerable interests in further strengthening relevant research from the perspective of both mechanism and technology. Consequently, the approaches used for and the consequences of PSCs for space applications are reviewed. This review provides an overview of recent progress in PSCs for space applications in terms of performance evolution and mechanism exploration of perovskite films and devices under space extreme environments.

Forest fires contribute to global greenhouse gas emissions and can negatively affect public health, economic activity, and provision of ecosystem services. In boreal forests, fires are a part of the ecosystem dynamics, while in the humid tropics, fires are largely human-induced and lead to forest degradation. Studies have shown changing fire dynamics across the globe due to both climate and land use change. However, global trends in fire-related forest loss remain uncertain due to the lack of a globally consistent methodology applied to high spatial resolution data. Here, we create the first global 30-m resolution satellite-based map of annual forest loss due to fire. When producing this map, we match the mapped area of forest loss due to fire to the reference area obtained using a sample-based unbiased estimator, thus enabling map-based area reporting and trend analysis. We find an increasing global trend in forest loss due to fire from 2001 to 2019, driven by near-uniform increases across the tropics, subtropical, and temperate Australia, and boreal Eurasia. The results quantify the increasing threat of fires to remaining forests globally and may improve modeling of future forest fire loss rates under various climate change and development scenarios.

Abstract. Land-cover change has been identified as an important cause or driving force of global climate change and is a significant research topic. Over the past few decades, global land-cover mapping has progressed; however, long-time-series global land-cover-change monitoring data are still sparse, especially those at 30 m resolution. In this study, we describe GLC_FCS30D, a novel global 30 m land-cover dynamics monitoring dataset containing 35 land-cover subcategories and covering the period 1985–2022 in 26 time steps (maps were updated every 5 years before 2000 and annually after 2000). GLC_FCS30D has been developed using continuous change detection and all available Landsat imagery based on the Google Earth Engine platform. Specifically, we first take advantage of the continuous change-detection model and the full time series of Landsat observations to capture the time points of changed pixels and identify the temporally stable areas. Then, we apply a spatiotemporal refinement method to derive the globally distributed and high-confidence training samples from these temporally stable areas. Next, local adaptive classification models are used to update the land-cover information for the changed pixels, and a temporal-consistency optimization algorithm is adopted to improve their temporal stability and suppress some false changes. Further, the GLC_FCS30D product is validated using 84 526 globally distributed validation samples from 2020. It achieves an overall accuracy of 80.88 % (±0.27 %) for the basic classification system (10 major land-cover types) and 73.04 % (±0.30 %) for the LCCS (Land Cover Classification System) level-1 validation system (17 LCCS land-cover types). Meanwhile, two third-party time-series datasets used for validation from the United States and Europe Union are also collected for analyzing accuracy variations, and the results show that GLC_FCS30D offers significant stability in terms of variation across the accuracy time series and achieves mean accuracies of 79.50 % (±0.50 %) and 81.91 % (±0.09 %) over the two regions. Lastly, we draw conclusions about the global land-cover-change information from the GLC_FCS30D dataset; namely, that forest and cropland variations have dominated global land-cover change over past 37 years, the net loss of forests reached about 2.5 million km2, and the net gain in cropland area is approximately 1.3 million km2. Therefore, the novel dataset GLC_FCS30D is an accurate land-cover-dynamics time-series monitoring product that benefits from its diverse classification system, high spatial resolution, and long time span (1985–2022); thus, it will effectively support global climate change research and promote sustainable development analysis. The GLC_FCS30D dataset is available via https://doi.org/10.5281/zenodo.8239305 (Liu et al., 2023).