Land Cover Classification System Research Articles

Land Cover Mapping in West Africa: A Collaborative Process

The availability of current land cover and land use (LCLU) information for monitoring the status of land resources has considerable value in ensuring sustainable land use planning and development. Similarly, the need to provide updated information on the extent of LCLU change in West Africa has become apparent, given the increasing demand for land resources driven by rapid population growth. Over the past decade, multiple projects have been undertaken to produce regional and national land cover maps. However, using different classification systems and legends has made updating and sharing land cover information challenging. This has resulted in the inefficient use of human and financial resources. The development of the Land Cover Meta Language (LCML) based on International Organization for Standardization (ISO) standards offers an opportunity to create a standardized classification system. This system would enable easier integration of regional and national data, efficient management of information, and better resource utilization in West Africa. This article emphasizes the process and the need for multistakeholder collaboration in developing a standardized land cover classification system for West Africa, which is currently nonexistent. It presents the survey data collected to evaluate historical, current, and future land cover mapping projects in the region and provides relevant use cases as examples for operationalizing a standardized land cover classification legend for West Africa.

Land Cover and Land Use Ontology—Evolution of International Standards, Challenges, and Opportunities

Knowledge of land is of central importance to manage the impact of mankind upon the environment. The understanding and treatment of land vary greatly across different regions and communities, making the description of land highly specific to each locality. To address the larger global issues, such as world food production or climate change mitigation, one needs to have a common standardized understanding of the biosphere cover and use of land. Different governments and institutions established national systems to describe thematic content of land within their jurisdictions. These systems are all valid and tuned to address various national needs. However, their integration at regional or global levels is lacking. Integrating data from widely divergent sources to create world datasets not only requires standards, but also an approach to integrate national and regional land cover classification systems. The ISO 19144 series, developed through the collaboration between the Food and Agriculture Organization of the United Nations (FAO) and the International Organization for Standardization (ISO), offers a meta-language for the integration of disparate land classification systems, enhancing interoperability, data sharing, and national to global data integration and comparison. This paper provides an overview of classification system concepts, different stages for the development of standards in ISO and the status of different standards in the ISO 19144 series. It also explores the critical role of the ISO 19144 series in standardizing land cover and land use classification systems. Drawing on practical case studies, the paper underscores the series’ potential to support global sustainable development goals and lays out a path for its future development and application. Using these standards, we gain not only a tool for harmonizing land classification, but also a critical level for advancing sustainable development and environmental stewardship worldwide.

Hierarchical-modular framework for habitat mapping through systematic and informed integration of remote sensing data with contextual information

Accurate and up-to-date habitat maps at national or regional levels are critical for informing conservation and restoration actions. Land cover maps generated from Earth Observation (EO) data can, to varying degrees, indicate the extent of some habitat categories but these are often insufficient in terms of the level of detail required. This study introduces a hierarchical-modular framework based on the globally applicable Food and Agriculture Organization (FAO) Land Cover Classification System (LCCS) whereby the land cover classes can be systematically translated to habitat categories and further differentiated by referencing contextual information and expert knowledge. Application is showcased for Wales (United Kingdom) where 10 m spatial resolution land cover maps were first constructed nationally from time-series of Sentinel-1C-band radar and Sentinel-2 optical data (2018–2020). The contextual datasets derived from non-EO sources were utilised to associate dominant vegetation types to detailed habitat classes.The accuracy assessment done using field survey data highlights that habitat classes directly derived from EO, including cultivated/managed and forest types, demonstrated higher mapping accuracies (>70% User's and Producer's Accuracies) compared to those that were more heavily dependent on non-EO-derived contextual information. These included neutral grasslands and fen/marsh/swamp that demonstrated lower accuracies (<20%) but also other detailed wetland classes (user's and producer's accuracies ranging from 25 to 60%). These reduced accuracies were largely associated with discrepancies in the contextual datasets used for their differentiation and mapping, and those integrated within field validation datasets. Dependency on contextual datasets diminished as detailed habitat maps were generalized into broader categories. The study proposes that, for enhanced habitat mapping, efforts should focus not only on EO data but also on maximising the accuracy and minimizing inconsistencies in contextual datasets as well as taxonomical systems. The flexible structure of the FAO LCCS hierarchical framework is also highlighted, emphasizing its adaptability for future improvements in habitat mapping by incorporating contextual datasets and more advanced algorithms that can improve EO-derived land cover descriptions.

SATELLITE LAND COVER CLASSIFICATION USING NEURAL NETWORK

This project develops a robust land cover classification system using CNNs for Sentinel-2 imagery, crucial for detecting land use changes and enhancing mapping. Leveraging Copernicus data ensures accessibility and integration into broader Earth observation initiatives, benefiting various fields. Keywords— Sentinel-2 imagery, Convolutional Neural Networks (CNNs), Copernicus program, remote sensing, land use changes, environmental studies, urban planning.

GLC_FCS30D: the first global 30 m land-cover dynamics monitoring product with a fine classification system for the period from 1985 to 2022 generated using dense-time-series Landsat imagery and the continuous change-detection method

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).

Dynamic monitoring of urban renewal based on multi-source remote sensing and POI data: A case study of Shenzhen from 2012 to 2020

Accurate information on the spatiotemporal distribution of urban renewal (UR) is important for sustainable urban development. Due to its complexity, existing studies could not completely describe the land cover types after demolition, and lacked the effective conversion rules to monitor the whole process of UR demolition and reconstruction which made it impossible to obtain high-precision UR extent, demolition time, and reconstruction time. This study proposed an UR monitoring framework by combining Point of Interest, nighttime light RS data, time-series RS data from Google Earth high-resolution and Landsat imageries. The urban vacant land was introduced to supplement the land cover classification system for UR monitoring and extracted by DeepLabv3 semantic segmentation model. The new conversion rules were then generated to track the historical changes in urban land types, and the multi-temporal classification model was applied to extract spatial and temporal characteristics of UR process. Results showed a total of 3,525.55 hm2 UR region were identified in Shenzhen during 2012–2020, and the largest demolition and reconstruction areas were both observed in 2019. The F1 and F2 scores of extracted UR extent, UR demolition time, and UR reconstruction time were larger than 0.72, 0.63 and 0.66, respectively, indicating high overall accuracies. Our proposed framework is important for the UR dynamic monitoring and can provide scientific basis for future urban construction.

A novel alpine land cover classification strategy based on a deep convolutional neural network and multi-source remote sensing data in Google Earth Engine

ABSTRACT Alpine land cover (ALC) is facing many challenges with climatic change, biodiversity reduction and other cascading ecosystem damage triggered by natural and anthropogenic interference. Although several global land cover products and thematic maps are already available, their mapping accuracy of alpine and montane regions remains unsatisfactory due to the data acquisition, methodology, and workflow design constraints. Therefore, in this paper, a deep convolutional neural network (DCNN) in Google Earth Engine (GEE) was developed to map the ALC types of the Yarlung Zangbo river basin (YZRB) in the Tibetan plateau using multi-source remote sensing data. The DCNN algorithm was offline trained using automatically generating samples and online deployed in the GEE for a large-scale ALC mapping. Moreover, a set of fine land cover classification system (containing 14 ALC types) was also established in accordance with the natural situation of the YZRB. The overall accuracy and kappa were 86.24% and 0.8156, which were higher than traditional classification algorithms. The spatial distribution of ALC types was analyzed in different gradient zones, and a clear altitudinal characteristic was noticed. The terrain of the YZRB from upper-stream to down-stream with an elevation dramatically decreases, and corresponding to vertical zonal changes from glacier and permanent snow/ice, barren gravel land, alpine desert steppe, alpine steppe, alpine meadow, shrubs, to tree cover. The product can provide valuable land cover information to support alpine ecosystem conservation.

Can the establishment of a protected area improve the lacustrine environment? A case study of Lake Chaohu, China

Eutrophication of lacustrine environments with frequent cyanobacterial blooms has become a serious problem. Overpopulation and runoff into groundwater and lakes from fertilizers with too much nitrogen and phosphorous have caused most of the problems. Here, we first devised a land use and cover classification system based on the local characteristics of the first-level protected area of Lake Chaohu (FPALC). Lake Chaohu is the fifth largest freshwater lake in China. The land use and cover change (LUCC) products were produced using sub-meter resolution satellite data from 2019 to 2021 in the FPALC. This study presents an evaluation of the effectiveness of the established protected areas. The results show the most impactful type was the reduction in cropland with an area that declined from 7446.4 hm2 to 6433.3 hm2 from 2019 to 2021. Most of the reduced cropland was converted into wetlands, with 460.2 hm2 and 152.0 hm2 of cropland restored to wetlands from 2019 to 2020 and 2020–2021, respectively. The area of cyanobacterial blooms in Lake Chaohu showed a downward trend, and the lacustrine environment was greatly improved after the establishment of the FPALC. These quantified data can inform decision-making related to Lake Chaohu conservation and provide a reference for managing the aquatic environment in other watersheds.

A dataset of land cover classifications with a spatial resolution of 30m in Mongolia in 2005 and 2015

The Mongolian Plateau is in the interior of Northeast Asia, and is extremely vulnerable to climate change and the deleterious effects of human activities. Mongolia is an important component unit of the Mongolian Plateau, and its resources, environment and ecological problems are closely related to the ecological barrier and resource security in northern China and the sustainable development of the China-Mongolia-Russia Corridor. However, there is still a lack of high-precision land cover data products suitable for the regional characteristics of Mongolia. In this study, according to the landscape pattern of Mongolia, we constructed a land cover classification system suitable for Mongolia; and based on the object-oriented remote sensing interpretation method, we adopted the split-scene interpretation to select a variety of indexes. According to certain rules and classification thresholds, we obtained a dataset of land cover classifications with a spatial resolution of 30m in Mongolia in 2005 and 2015. The land cover classifications of Mongolia includes 11 categories: forest, meadow steppe, real steppe, desert steppe, bare land, sand, desert, ice and snow, water, cropland and built areas. Based on multi-source validation point information and high-resolution Google Earth images, we completed an overall quality assessment and a single classification quality assessment of land cover classification results in Mongolia. In 2005, the overall classification accuracy is 78.85% and the Kappa coefficient is 0.77. In 2015, the overall classification accuracy is 80.49% and the Kappa coefficient is 0.78. The average annual classification accuracy is 79.67%, which meets the accuracy requirements. The dataset can directly reflect the changes of land cover pattern and trend in Mongolia and provide basic scientific data to support the sustainable development of Mongolia.

Soil monitoring and land cover/land use assessment on the Blue Nile River Watershed, Blue Nile State – Sudan/ using remote sensing and other techniques

The study was carried out along the course of the Blue Nile from the Ethiopian-Sudanese border in the south to the borders of the Blue Nile state with Sennar state in the north. The study area was determined by establishing a buffer around the course of the Blue Nile, with a width of 20 km (10 km at each side of the river), Blue Nile state. The study attempted to update some information in the study area regarding land use/ land cover, soil properties and contour map. To facilitate forest inventory and field work. The study area was divided into equal area to four zones (A, B, C and D), 783 sites and soil sample samples were taken and classified using the land cover classification system (LCCS). The fieldwork and survey began with four practical groups, a group for each zone within the period 1 December 2015 to 5 March, 2016 in a total area of approximately 346483.42 ha. Remote sensing and fieldwork data analysis showed that there are significant changes in land use/ land cover and soil properties are in the study area (1990 to 2015). Zones A and B (South of Rosieris Dam) are mainly composed of clay soil, while the soil of Zones C and D (North of Rosieris dam) is mainly loamy soil. the study indicate that 13%, 11%, 22% and 19% from zone A, B, C and D respectively lies within the slightly acidity (pH 5.5 to 6.5), while 87%, 87%, 78% and 81% of the same zone respectably was natural soil and 2% of zone B classified as Slightly alkaline soil (pH 8) and more than 50% of the total area classified as neutral to slightly acidity, which is suitable for most crops and natural vegetation covers. SP% analysis showed that more than 80% of soils samples in the study area have SP% values greater than 40% which characterized combination of silt, loam and clay. The study indicate that the change in the patterns of land cover/ land use systems is found to be mainly due to civil war and economic crises with no clear signs of climatic change.

Міжнародні системи класифікації земного покриву та землекористування: особливості і перспективи використання у ландшафтознавчих дослідженнях

The purpose of the paper is to review the international systems of classification of land cover and land use, which are most often used in landscape or related research in Ukraine – CORINE, LUCAS, EUNIS, LCCS, GlobeLand 30; to identify those features of each of the systems that may become a priority in landscape studies in different areas. Applying general scientific methods of cognition (analysis, synthesis, abstraction, generalization, comparative), methodological and technical manuals representing the classification systems of land cover and land use have been studied. Domestic and foreign papers on landscape, ecology, cartography, in which the systems are used for solving applied tasks have also been examined. The use of one of the developed classification systems in a particular study depends on its purpose, scale, source data and details of field observation materials. Special attention is paid to the use of land cover maps to identify changes occurring within landscapes over a period of time. Classification systems, in the nomenclature of classes of which land use categories predominate, can be basic for works in the field of anthropogenic landscape science, and in the genetic field, the key categories of classification systems are categories of land cover. For recent research, the base is the map of landscape complexes, the rank of which depends on the scale of mapping the area. Field research also retains its decisive role. The use of land cover classification systems, which include field surveys, such as LUCAS and EUNIS, logically fits into large-scale research.

Innovative Analysis Ready Data (ARD) product and process requirements, software system design, algorithms and implementation at the midstream as necessary-but-not-sufficient precondition of the downstream in a new notion of Space Economy 4.0 - Part 2: Software developments

ABSTRACT Aiming at the convergence between Earth observation (EO) Big Data and Artificial General Intelligence (AGI), this paper consists of two parts. In the previous Part 1, existing EO optical sensory image-derived Level 2/Analysis Ready Data (ARD) products and processes are critically compared, to overcome their lack of harmonization/ standardization/ interoperability and suitability in a new notion of Space Economy 4.0. In the present Part 2, original contributions comprise, at the Marr five levels of system understanding: (1) an innovative, but realistic EO optical sensory image-derived semantics-enriched ARD co-product pair requirements specification. First, in the pursuit of third-level semantic/ontological interoperability, a novel ARD symbolic (categorical and semantic) co-product, known as Scene Classification Map (SCM), adopts an augmented Cloud versus Not-Cloud taxonomy, whose Not-Cloud class legend complies with the standard fully-nested Land Cover Classification System’s Dichotomous Phase taxonomy proposed by the United Nations Food and Agriculture Organization. Second, a novel ARD subsymbolic numerical co-product, specifically, a panchromatic or multi-spectral EO image whose dimensionless digital numbers are radiometrically calibrated into a physical unit of radiometric measure, ranging from top-of-atmosphere reflectance to surface reflectance and surface albedo values, in a five-stage radiometric correction sequence. (2) An original ARD process requirements specification. (3) An innovative ARD processing system design (architecture), where stepwise SCM generation and stepwise SCM-conditional EO optical image radiometric correction are alternated in sequence. (4) An original modular hierarchical hybrid (combined deductive and inductive) computer vision subsystem design, provided with feedback loops, where software solutions at the Marr two shallowest levels of system understanding, specifically, algorithm and implementation, are selected from the scientific literature, to benefit from their technology readiness level as proof of feasibility, required in addition to proven suitability. To be implemented in operational mode at the space segment and/or midstream segment by both public and private EO big data providers, the proposed EO optical sensory image-derived semantics-enriched ARD product-pair and process reference standard is highlighted as linchpin for success of a new notion of Space Economy 4.0.

The Verification of Land Cover Datasets with the Geo-Tagged Natural Scene Images

Land cover is important for global change studies, and its accuracy and reliability are usually verified by field sampling, which costs a lot. A method was proposed for the verification of land cover datasets with the geo-tagged natural scene images using a convolutional neural network. The nature scene images were firstly collected from the Land Use and Cover Area frame Survey (LUCAS) and global crowdsourcing images platform Flickr, then classified according to the Land Cover Classification System. The Nature Scene Image Classification (NSIC) model based on the GoogLeNet Inception network for recognition of natural scene images was then constructed. Finally, in the UK, as a verification area, the European Space Agency Climate Change Initiative Land Cover (ESA CCI-LC) datasets and the Global land-cover product with fine classification system (GLC-FCS) were verified using the NSIC-Inception model with the nature scene image set. The verification results showed that the overall accuracy verified by LUCAS was very close to the accuracy of the land cover product, which was 94.41% of CCI LC and 92.89% of GLC-FCS, demonstrating the feasibility of using geo-tagged images classified by the NSIC model. In addition, the VGG16 and ResNet50 were compared with GoogLeNet Inception. The differences in verification between LUCAS and Flickr images were discussed regarding the image’s quantity, the spatial distribution, the representativeness, and so on. The uncertainties of verification arising from differences in the spatial resolution of the different datasets were explored by CCI LC and GCL-FCS. The application of the method has great potential to support and improve the efficiency of land cover verification.

Operational continental-scale land cover mapping of Australia using the Open Data Cube

ABSTRACT To comprehensively support national and international initiatives for sustainable development, land cover products need to be reliably and routinely generated within operational frameworks. Coupled with consistent semantics and taxonomies, ensuring confidence in mapping land cover for multiple time periods, facilitates informed decision-making at scales appropriate to multiple policy domains. The United Nations Food and Agriculture Organisation (FAO) Land Cover Classification System (LCCS) provides a taxonomy that comparable at different scales, level of detail and geographic location. The Open Data Cube (ODC) initiative offers a framework for operational continental-scale land cover mapping using analysis-ready Earth Observation data. This study utilised the FAO LCCS framework and the Landsat sensor data through Digital Earth Australia (DEA; Australia’s ODC instance) to generate consistent and continent-wide land cover mapping (DEA Land Cover) of the Australian continent. DEA Land Cover provides annual maps from 1988 to 2020 at 25 m resolution. Output maps were validated with ∼12,000 independent validation points, giving an overall map accuracy of 80%. DEA Land Cover provides Australia with a nationally consistent picture of land cover, with an open-source software package using readily available global coverage data and demonstrates a pathway of adoption for national implementations across the world.

Implications of Spatio-Temporal Land Use/Cover Changes for Ecosystem Services Supply in the Coastal Landscapes of Southwestern Ghana, West Africa

Land use/land cover change (LULCC) is an important driver of ecosystem changes in coastal areas. Despite being pervasive in coastal Ghana, LULCC has not been investigated to understand its effects on the potential for coastal landscapes to supply ecosystem services (ES). In this study, the impacts of LULCC on the potential supply of ES by coastal landscapes in Southwestern Ghana was assessed for the years 2008 and 2018 by using remote sensing and benefit transfer approaches. Based on available data, relevant provisioning and regulating ES were selected for the assessment while indicators to aid the quantification of the ES were obtained from literature. Supervised classification methods and maximum likelihood algorithms were used to prepare land use/land cover (LULC) maps and the derived LULC categories were assigned according to the descriptions of the Land Cover Classification System (LCCS). Potential supply of provisioning (food, fuelwood) and regulating (carbon storage) services was quantified and the spatial and temporal distributions of these ES illustrated using maps. The results show variations in food and fuelwood supply and carbon storage potentials over the study period and across different locations on the landscape. Potentials for fuelwood supply and carbon storage in mangrove forests indicated declining trends between 2008 and 2018. On the other hand, food-crop supply and carbon storage potential in rubber plantations depicted increasing patterns over the same period. Population, slope and elevation exhibited strong effects on LULC conversions to food crop and rubber plantations whereas these factors were less important determinants of mangrove forest conversions. The findings of the study have implications for identifying and addressing tradeoffs between land uses for agriculture, industrial development and conservation of critical coastal ES within the context of rapid land system transformations in the study region.

An Integrated Approach of Machine Learning, Remote Sensing, and GIS Data for the Landslide Susceptibility Mapping

Landslides triggered in mountainous areas can have catastrophic consequences, threaten human life, and cause billions of dollars in economic losses. Hence, it is imperative to map the areas susceptible to landslides to minimize their risk. Around Abbottabad, a large city in northern Pakistan, a large number of landslides can be found. This study aimed to map the landslide susceptibility over these regions in Pakistan by using three Machine Learning (ML) techniques, specifically Linear Regression (LiR), Logistic Regression (LoR), and Support Vector Machine (SVM). Several influencing factors were used to identify the potential landslide areas, including elevation, slope degree, slope aspect, general curvature, plan curvature, profile curvature, landcover classification system, Normalized Difference Water Index (NDWI), Normalized Difference Vegetation Index (NDVI), soil, lithology, fault density, topographic roughness index, and road density. The weights of these factors were calculated using ML techniques. The weightage overlay tool is adopted to map the final output. According to three ML models, lithology, NDWI, slope, and LCCS significantly impact landslide occurrence. The area under the ROC curve (AUC) is applied to validate the performance of models, and the results show the AUC value of LiR (88%) is better than SVM (86%) and LoR (85%) models. ML models and final susceptibility map gives good accuracy, which can be reliable for the results. The study’s outcome provides baselines for policymakers to propose adequate protection and mitigation measures against the landslides in the region, and any other researcher can adopt this methodology to map the landslide susceptibility in another area having similar characteristics.

Constraining a land cover map with satellite-based aboveground biomass estimates over Africa

Abstract. Most land surface models can, depending on the simulation experiment, calculate the vegetation distribution and dynamics internally by making use of biogeographical principles or use vegetation maps to prescribe spatial and temporal changes in vegetation distribution. Irrespective of whether vegetation dynamics are simulated or prescribed, it is not practical to represent vegetation across the globe at the species level because of its daunting diversity. This issue can be circumvented by making use of 5 to 20 plant functional types (PFTs) by assuming that all species within a single functional type show identical land–atmosphere interactions irrespective of their geographical location. In this study, we hypothesize that remote-sensing-based assessments of aboveground biomass can be used to constrain the process in which real-world vegetation is discretized in PFT maps. Remotely sensed biomass estimates for Africa were used in a Bayesian framework to estimate the probability density distributions of woody, herbaceous and bare soil fractions for the 15 land cover classes, according to the United Nations Land Cover Classification System (UN-LCCS) typology, present in Africa. Subsequently, the 2.5th and 97.5th percentiles of the probability density distributions were used to create 2.5 % and 97.5 % credible interval PFT maps. Finally, the original and constrained PFT maps were used to drive biomass and albedo simulations with the Organising Carbon and Hydrology In Dynamic Ecosystems (ORCHIDEE) model. This study demonstrates that remotely sensed biomass data can be used to better constrain the share of dense forest PFTs but that additional information on bare soil fraction is required to constrain the share of herbaceous PFTs. Even though considerable uncertainties remain, using remotely sensed biomass data enhances the objectivity and reproducibility of the process by reducing the dependency on expert knowledge and allows assessing and reporting the credible interval of the PFT maps which could be used to benchmark future developments.

A Methodology to Generate Integrated Land Cover Data for Land Surface Model by Improving Dempster-Shafer Theory

Land cover type is a key parameter for simulating surface processes in many land surface models (LSMs). Currently, the widely used global remote sensing land cover products cannot meet the requirements of LSMs for classification systems, physical definition, data accuracy, and space-time resolution. Here, a new fusion method was proposed to generate land cover data for LSMs by fusing multi-source remote sensing land cover data, which was based on improving Dempster-Shafer evidence theory with mathematical models and knowledge rules optimization. The new method has the ability to deal with seriously disagreement information, thereby improving the robustness of the theory. The results showed the new method can reduce the disagreement between input data and realized the conversion of multiple land cover classification systems to into a single land cover classification system. China Fusion Land Cover data (CFLC) in 2015 generated by the new method maintained the classification accuracy of the China land use map (CNLULC), which is based on visual image interpretation and further enriched land cover classes of input data. Compared with Geo-Wiki observations in 2015, the overall accuracy for CFLC is higher than other two global land cover data. Compared with the observations, the 0–10 cm soil moisture simulated by the CFLC in Noah–MP LSM during the growing season in 2014 had better performance than that simulated by initial land cover data and MODIS land cover data. Our new method is highly portable and generalizable to generate higher quality land cover data with a specific land cover classification system for LSMs by fusing multiple land cover data, providing a new approach to land cover mapping for LSMs.

Developments in Land Use and Land Cover Classification Techniques in Remote Sensing: A Review

Studies on land use and land cover changes (LULCC) have been a great concern due to their contribution to the policies formulation and strategic plans in different areas and at different scales. The LULCC when intense and on a global scale can be catastrophic if not detected and monitored affecting the key aspects of the ecosystem’s functions. For decades, technological developments and tools of geographic information systems (GIS), remote sensing (RS) and machine learning (ML) since data acquisition, processing and results in diffusion have been investigated to access landscape conditions and hence, different land use and land cover classification systems have been performed at different levels. Providing coherent guidelines, based on literature review, to examine, evaluate and spread such conditions could be a rich contribution. Therefore, hundreds of relevant studies available in different databases (Science Direct, Scopus, Google Scholar) demonstrating advances achieved in local, regional and global land cover classification products at different spatial, spectral and temporal resolutions over the past decades were selected and investigated. This article aims to show the main tools, data, approaches applied for analysis, assessment, mapping and monitoring of LULCC and to investigate some associated challenges and limitations that may influence the performance of future works, through a progressive perspective. Based on this study, despite the advances archived in recent decades, issues related to multi-source, multi-temporal and multi-level analysis, robustness and quality, scalability need to be further studied as they constitute some of the main challenges for remote sensing.

Deep Learning Models Performance Evaluations for Remote Sensed Image Classification

Deep learning-based land cover and land use (LCLU) classification systems are a significant aspiration for remote sensing communities. In nature, remote sensing images have various properties that need to be analyzed. Analyzing and interpreting image properties is difficult due to the nature of the image, the sensor technology’s capability, and other determinant variables such as seasons and weather conditions. The problem is essential for environmental monitoring, agricultural decision-making, and urban planning if it can be supported by deep learning systems. Therefore, deep learning approaches are proposed to quickly analyze and interpret the remote sensing image to classify the LCLU. The deep learning methods could be designed starting from scratch or using pre-trained networks. However, there are few comparisons of deep learning methods developed from scratch and trained on pre-trained networks. Thus, we proposed evaluating and comparing the deep learning models convolutional neural network feature extractor (CNN-FE) by developing it from scratch, transfer learning, and fine-tuning it for the LCLU classification system using remote sensed images. Using CNN-FE, TL, and fine-tuning deep learning models as examples, this paper compares and analyzes deep learning algorithms for remote sensed image classification. After developing and training each deep learning model on the UCM dataset, we evaluated and compared their performances using the performance measurement metrics accuracy, precision, recall, f1-score, and confusion matrix. The proposed deep learning algorithms can adapt and learn the features of the remote sensing images, and the TL and fine-tuning classification performances are significantly improved. As a result of the efficient time used for training the models, this paper discovered that the fine-tuned deep learning model achieved profound accuracy performance results in the UCM dataset.