Annual Land Cover Research Articles

Annual satellite-based NDVI-derived land cover of Europe for 2001–2019

Land cover plays an important role in the Earth's climate as it affects multiple biochemical cycles and is critical for food security and biodiversity. As land cover is continuously evolving, influenced by anthropogenic and other factors, the availability of temporally varying land cover data sets of large spatial domains is integral to understanding, monitoring, and informing environmental management efforts. Here we use classification trees to generate annual land cover maps of the European continent for 2001 to 2019 on a ∼250 m resolution. The classification trees are trained using gap-filled and smoothed MODIS normalised difference vegetation index (NDVI) satellite data, as well as CORINE reference land cover data. We apply the bagging ensemble technique on oversampled NDVI data, with an additional majority vote for overlapping segments over the continent-wide domain. We distinguish between 39 land cover classes, with a total classification accuracy of 75% and average precision of 76%. The accuracy varies between the classes, with common classes (e.g. agricultural and forest classes) performing better than rarer ones (e.g. artificial land cover). Over the entire continent, we find that artificial land cover, wetlands, and forests have increased on average by 0.76, 0.50 and 0.22%/year respectively, while the agricultural area has decreased by 0.21%/year. We also quantify these changes in land cover on a national and metropolitan level. Given the near-real-time availability of global NDVI data, we note the potential of the presented approach for generating ‘near-real-year’ annual land cover data sets of large geographic domains, for the continuous monitoring of land cover change and the effects of interventions.

The heterogeneous effects of agricultural conservation easements on the loss of farmland to development in New England

Farmland near cities can provide diverse non-market benefits, such as recreational open space, landscape appeal, local food production, ecological habitat, and water regulation, which risk being underprovided by markets in the absence of intervention. The rapid loss of farmland to development has long been a concern of conservation non-profits and policymakers in the U.S. and globally, which has recently gained traction due to President Biden's decision to include farmlands in the federal goal to protect 30% of U.S. land by 2030. Agricultural conservation easements are a widespread policy tool to protect farmland from conversion to development in the long term. However, the extent to which these easements causally reduce farmland loss to development within their boundaries is rarely studied at the spatial scale at which easement adoption decisions are made: the individual parcel. Here we estimate the impacts of agricultural conservation easements on farmland loss at the parcel level at a large spatial scale and over a long time horizon. Our case study from six New England states uses a rich dataset of 1.97 million parcels, novel estimates of annual parcel-level land cover change from 1988 to 2016, and quasi-experimental counterfactual estimation strategies to estimate the extent to which 3,959 farmland easements causally avoided conversion of cropland to development. Our results suggest that agricultural conservation easements have significantly reduced farmland loss to development. However, the overall magnitude of avoided rates of farmland loss on easements is very small (0.0067% ± 0.0019% of parcel area per annum), largely because of a low background rate of farmland loss across New England (0.0027% of total area per annum). A spatial allocation of agricultural easements towards more rapidly urbanizing counties (with farmland loss rates of up to 0.0281% of county area per annum) would increase the causal impacts of this instrument. Overall, our findings suggest that the spatial allocation of farmland easements has historically not prioritized the highest-threat locations where impacts would be most noticeable, indicating that allocation is driven by a variety of goals in addition to avoiding farmland loss.

Exacerbated drought impacts on global ecosystems due to structural overshoot.

Vegetation dynamics are affected not only by the concurrent climate, but also by memory-induced lagged responses. For example, favorable climate in the past could stimulate vegetation growth to surpass the ecosystem carrying capacity, leaving an ecosystem vulnerable to climate stresses. This phenomenon, known as structural overshoot, could potentially contribute to worldwide drought stress and forest mortality, but the magnitude of the impact is poorly known due to the dynamic nature of overshoot and complex influencing timescales. Here we use a dynamic statistical learning approach to identify and characterize ecosystem structural overshoot globally, and quantify the associated drought impacts. We find that structural overshoot contributed to around 11% of drought events during 1981–2015, and is often associated with compound extreme drought and heat, causing faster vegetation declines and greater drought impacts compared to non-overshoot related droughts. The fraction of droughts related to overshoot is strongly related to mean annual temperature, with biodiversity, aridity, and land cover as secondary factors. These results highlight the large role vegetation dynamics play in drought development, and suggest that soil water depletion due to warming-induced future increases in vegetation could cause more frequent and stronger overshoot droughts.

Land cover changes on a barrier island: Yearly changes, storm effects, and recovery periods

Ecosystems on barrier islands provide socio-ecological services to terrestrial and aquatic endangered species, as well as human inhabitants. The management of these coastal ecosystems is challenged by changes in annual and storm time scales driven by atmospheric, oceanographic, geologic, and human processes. Thus, the need for data and methods to accurately quantify and assess ecosystem and land cover evolution to inform stakeholders is on the rise. A dataset of high-resolution color infrared images of a U.S. National Wildlife Refuge is used to quantify annual land cover changes at a barrier island scale and to identify the effects of hurricanes and their recovery periods. Geospatial analysis and change matrices depict the interconnection between 13 land cover classes. Vegetation growth over regions of bare sand formed by storms leads to the creation of successional habitats, while the loss of bare sand dune to beach, and beach to water are indicators of erosional processes. Storms passing along the ocean and sound side of a barrier island result in different land cover changes that can last anywhere from 4 to more than 7 years, respectively. Management practices for coastal regions and the presence of infrastructure partially control the expansion of marshes, bare sand, maritime brush, and dunes.

A novel automatic phenology learning (APL) method of training sample selection using multiple datasets for time-series land cover mapping

The long record of Landsat imagery, which is the cornerstone of Earth observation, provides an opportunity to monitor land use and land cover (LULC) change and understand the interactions between the climate and earth system through time. A few change detection algorithms such as Continuous Change Detection and Classification (CCDC) have been developed to utilize all available Landsat images for change detection and characterization at local or global scales. However, the reliable, rapid, and reproducible collection of training samples have become a challenge for time series land cover classification at a large scale. To meet the challenge, we proposed an automatic phenology learning (APL) method with the assumption that the temporal profiles of samples within the same land cover type are the same or similar at a local scale to generate evenly distributed training samples automatically. We designed the method to build land cover patterns for each category based on consensus samples derived from multiple existing scientific datasets including LANDFIRE's (LF) Existing Vegetation Type (EVT), USGS National Land Cover Database (NLCD), National Agricultural Statistics Service (NASS) Cropland Data Layer (CDL), and National Wetlands Inventory (NWI). Then we calculated the Time-Weighted Dynamic Time Warping (twDTW) distance between any undefined samples and land cover patterns in the same geographical region as prior knowledge. Finally, we selected the optimal land cover category for each undefined sample from the land cover products based on the designed criteria iteratively using the twDTW distance as an indicator. The method was applied in the footprint of 10 selected Landsat Analysis Ready Data (ARD) tiles in the eastern and western conterminous United States (CONUS) to produce annual land cover maps from 1985 to 2017. The accuracy assessment and visual comparison revealed that the APL method can generate reliable training samples without any manual interpretation, producing better land cover results especially for the grass/shrub and wetland land cover classes. Applying the APL method, the overall accuracy of the annual land cover maps was improved by 2% over the accuracy of Land Change Monitoring, Assessment, and Projection (LCMAP) Collection 1.0 Science Products in the research regions. Our results also indicate that the APL method provides an approach for best use of different land cover products and meets the requirement of intensive sampling for training data collection.

Towards operational validation of annual global land cover maps

Annual global land cover maps (GLC) are being provided by several operational monitoring efforts. However, map validation is lagging, in the sense that the annual land cover maps are often not validated. Concurrently, users such as the climate and land management community require information on the temporal consistency of multi-date GLC maps and stability in their accuracy. In this study, we propose a framework for operational validation of annual global land cover maps using efficient means for updating validation datasets that allow timely map validation according to recommendations in the CEOS Stage-4 validation guidelines. The framework includes a regular update of a validation dataset and continuous map validation. For the regular update of a validation dataset, a partial revision of the validation dataset based on random and targeted rechecking (areas with a high probability of change) is proposed followed by additional validation data collection. For continuous map validation, an accuracy assessment of each map release is proposed including an assessment of stability in map accuracy addressing the user needs on the temporal consistency information of GLC map and map quality. This validation approach was applied to the validation of the Copernicus Global Land Service GLC product (CGLS-LC100). The CGLS-LC100 global validation dataset was updated from 2015 to 2019. The update was done through a partial revision of the validation dataset and an additional collection of sample validation sites. From the global validation dataset, a total of 40% (10% for each update year) was revisited, supplemented by a targeted revision focusing on validation sample locations that were identified as possibly changed using the BFAST time series algorithm. Additionally, 6720 sample sites were collected to represent possible land cover change areas within 2015 and 2019. Through this updating mechanism, we increased the sampling intensity of validation sample sites in possible land cover change areas within the period. Next, the dataset was used to validate the annual GLC maps of the CGLS-LC100 product for 2015–2019. The results showed that the CGLS-LC100 annual GLC maps have about 80% overall accuracy showing high temporal consistency in general. In terms of stability in class accuracy, herbaceous wetland class showed to be the least stable over the period. As more operational land cover monitoring efforts are upcoming, we emphasize the importance of updated map validation and recommend improving the current validation practices and guidelines towards operational map validation so that long-term land cover maps and their uncertainty information are well understood and properly used.

Spatial-temporal evolution of landscape degradation on the Guamá River Basin, Brazil

The goal of this study was to determine the anthropization evolution of the Guamá river basin in the years 2000, 2008 and 2018 by means of the Anthropic Transformation Index. Land use and cover maps were obtained from two databases, Project Mapbiomas (Brazilian Annual Land Use and Land Cover Mapping Project) and PRODES (Project for the Satellite Monitoring of the Brazilian Amazon Forest). The main classes defined in the mapping process are: forest, natural non-forest vegetation, agriculture and livestock farming, secondary vegetation, urban infrastructure, water and others. Secondary vegetation was considered as the area where the forest classes of Mapbiomas intersects with the deforested areas of PRODES, as determined by the map algebra operator. The expansion of agriculture and livestock farming achieved an increase of about 10%, while the forest was reduced in almost 10%. The Guamá river basin obtained an Anthropic Transformation Index of 4.44 in 2000, 5.04 in 2008 and 5.09 in 2018, going from a regular to a degraded state in 18 years. The occupation process caused major alterations in the natural components of the landscape over the course of 18 years, notably in the amount of forest. Protection of 35% of the remnant primary forest in the Guamá river basin is vital for the conservation of water resources vulnerable to changes in land use.

The relationships between economic growth and cropland changes in Bangladesh: An evidence based on annual land cover data

Bangladesh is experiencing rapid economic progress since 1990s, at the same time, facing acute shortage of agricultural land. Using 19 years (2000-2018) time series remote-sensing data and Random Forest machine learning algorithm in Google Earth Engine (GEE), this study classifies the land covers in Bangladesh; determines the trend of land cover changes using least-square growth rate model; and finds the associations between the trends of cropland and growth of socio-economic factors using correlation and regression analysis. The annual average area of cropland decline is 29271 hectare, which is higher than the absolute changes of other major land covers, such as forest (25932 hectare) and built-up area (1649 hectare). With the annual growth of urban population (3.81%) and gross domestic product (GDP) (6.28%), the predicted declining rate of cropland is estimated 0.29%, which is very close to the observed annual declining rate (0.28%). However, the partial effects of urban population and GDP could not be detected. Therefore, the study infers that urbanization and economic growth in Bangladesh are happening simultaneously. As a result, the joint determination of both phenomena can explain the degradation of agricultural land in Bangladesh.

Validation of the U.S. Geological Survey's Land Change Monitoring, Assessment and Projection (LCMAP) Collection 1.0 annual land cover products 1985–2017

The U.S. Geological Survey Land Change Monitoring, Assessment and Projection (USGS LCMAP) has released a suite of annual land cover and land cover change products for the conterminous United States (CONUS). The accuracy of these products was assessed using an independently collected land cover reference sample dataset produced by analysts interpreting Landsat data, high-resolution aerial photographs, and other ancillary data. The reference sample of nearly 25,000 pixels and the accompanying 33-year time series of annual land cover reference labels allowed for a comprehensive assessment of accuracy of the LCMAP land cover and land cover change products. Overall accuracy (± standard error) for the per-pixel assessment across all years for the eight land cover classes was 82.5% (±0.2%). Overall accuracy was consistent year-to-year within a range of 1.5% but varied regionally with lower accuracy in the eastern United States. User's accuracy (UA) and producer's accuracy (PA) for CONUS ranged from the higher accuracies of Water (UA = 96%, PA = 93%) and Tree Cover (UA = 90%, PA = 83%) to the lower accuracies of Wetland (UA = 69%, PA = 74%) and Barren (UA = 43%, PA = 57%). For a binary change/no change classification, UA of change was 13% (±0.5%) and PA was 16% (±0.6%) for CONUS when agreement was defined as a match by the exact year of change. UA and PA improved to 28% and 34% when agreement was defined as the change being detected by the map and reference data within a ± 2-year window. Change accuracy was higher in the eastern United States compared to the western US. UA was 49% (±0.3) and PA was 54% (±0.3) for the footprint of change (defined as the area experiencing at least one land cover change from 1985 to 2017). For class-specific loss and gain when agreement was defined as an exact year match, UA and PA were generally below 30%, with Tree Cover loss being the most accurately mapped change (UA = 25%, PA = 31%). These accuracy results provide users with information to assess the suitability of LCMAP data and information to guide future research for improving LCMAP products, particularly focusing on the challenges of accurately mapping annual land cover change.

The 30 m annual land cover dataset and its dynamics in China from 1990 to 2019

Abstract. Land cover (LC) determines the energy exchange, water and carbon cycle between Earth's spheres. Accurate LC information is a fundamental parameter for the environment and climate studies. Considering that the LC in China has been altered dramatically with the economic development in the past few decades, sequential and fine-scale LC monitoring is in urgent need. However, currently, fine-resolution annual LC dataset produced by the observational images is generally unavailable for China due to the lack of sufficient training samples and computational capabilities. To deal with this issue, we produced the first Landsat-derived annual China land cover dataset (CLCD) on the Google Earth Engine (GEE) platform, which contains 30 m annual LC and its dynamics in China from 1990 to 2019. We first collected the training samples by combining stable samples extracted from China's land-use/cover datasets (CLUDs) and visually interpreted samples from satellite time-series data, Google Earth and Google Maps. Using 335 709 Landsat images on the GEE, several temporal metrics were constructed and fed to the random forest classifier to obtain classification results. We then proposed a post-processing method incorporating spatial–temporal filtering and logical reasoning to further improve the spatial–temporal consistency of CLCD. Finally, the overall accuracy of CLCD reached 79.31 % based on 5463 visually interpreted samples. A further assessment based on 5131 third-party test samples showed that the overall accuracy of CLCD outperforms that of MCD12Q1, ESACCI_LC, FROM_GLC and GlobeLand30. Besides, we intercompared the CLCD with several Landsat-derived thematic products, which exhibited good consistencies with the Global Forest Change, the Global Surface Water, and three impervious surface products. Based on the CLCD, the trends and patterns of China's LC changes during 1985 and 2019 were revealed, such as expansion of impervious surface (+148.71 %) and water (+18.39 %), decrease in cropland (−4.85 %) and grassland (−3.29 %), and increase in forest (+4.34 %). In general, CLCD reflected the rapid urbanization and a series of ecological projects (e.g. Gain for Green) in China and revealed the anthropogenic implications on LC under the condition of climate change, signifying its potential application in the global change research. The CLCD dataset introduced in this article is freely available at https://doi.org/10.5281/zenodo.4417810 (Yang and Huang, 2021).

Hotter Drought Escalates Tree Cover Declines in Blue Oak Woodlands of California

California has, in recent years, become a hotspot of interannual climatic variability, recording devastating climate-related disturbances with severe effects on tree resources. Understanding the patterns of tree cover change associated with these events is vital for developing strategies to sustain critical habitats of endemic and threatened vegetation communities. We assessed patterns of tree cover change, especially the effects of the 2012–2016 drought within the distribution range of blue oak (Quercus douglasii), an endemic tree species to California with a narrow geographic extent. We utilized multiple, annual land-cover and land-surface change products from the U.S. Geological Survey (USGS) Land Change Monitoring, Assessment and Projection (LCMAP) project along with climate and wildfire datasets to monitor changes in tree cover state and condition and examine their relationships with interannual climate variability between 1985 and 2016. Here, we refer to a change in tree cover class without a land-cover change to another class as “conditional change.” The unusual drought of 2012–2016, accompanied by anomalously high temperatures and vapor pressure deficit, was associated with exceptional spikes in the amount of both fire and non-fire induced tree cover loss and tree cover conditional change, especially in 2015 and 2016. Approximately 1,266 km2 of tree cover loss and 617 km2 of tree cover conditional change were recorded during that drought. Tree cover loss through medium to high severity fires was especially large in exceptionally dry and hot years. Our study demonstrates the usefulness of the LCMAP products for monitoring the effects of climatic extremes and disturbance events on both thematic and conditional land-cover change over a multi-decadal period. Our results signify that blue oak woodlands may be vulnerable to extreme climate events and changing wildfire regimes. Here, we present early evidence that frequent droughts associated with climate warming may continue to affect tree cover in this region, while drought interaction with wildfires and the resulting feedbacks may have substantial influence as well. Consequently, efforts to conserve the blue oak woodlands, and potentially other vegetation communities in the Western United States, may benefit from consideration of climate risks as well as the potential for climate-fire and vegetation feedbacks.

Assessment of basin-scale groundwater potentiality mapping in drought-prone upper Dwarakeshwar River basin, West Bengal, India, using GIS-based AHP techniques

Sustainable use of groundwater is essential in any region to increase long-term agricultural sustainability as well as to maintain the pace of socio-economic development of the region. Groundwater is a most vital and valuable natural resource for ecosystems and communities in the drought-prone western part of West Bengal, India. The intensity of agriculture in drought-prone areas has resulted in the expansion of groundwater. The current study has been conducted in a semi-arid upper Dwarakeshwar River basin which is basically a meteorological as well as agricultural drought-prone and agro-economy-based region. The current paper attempts to illustrate the areas of groundwater potentiality by using Analytical Hierarchy Process (AHP) and Geographic Information System (GIS). Appropriate weight has been determined for each factor and their subclasses on the basis of their relative importance by using the AHP technique. The final output map has been integrated by using total twelve sets of groundwater influencing thematic layers, namely: aquifer media, mean annual groundwater level, lithology, land use and land cover, rainfall, drainage density, soil drainage, soil texture, Normalized Difference Vegetation Index (NDVI), elevation, curvature, and slope. It has been classified into five zones: very poor, poor, moderate, well, and excellent covering an area of 256.87 km2 (13.38%), 581.79 km2 (30.30%), 607.91 km2 (31.66%), 381.58 km2 (19.87%), and 91.36 km2 (4.76%), respectively, and finally, results have been validated with the help of mean annual groundwater level data of 50 dug wells through the Receiver Operating Characteristic (ROC) curve. The result of Area Under Curve (AUC) value is 0.871 that indicates 87.1% accuracy and reliability for better planning, management, and resource development in an effective way.

Mapping fine-scale human disturbances in a working landscape with Landsat time series on Google Earth Engine

Large fractions of human-altered lands are working landscapes where people and nature interact to balance social, economic, and ecological needs. Achieving these sustainability goals requires tracking human footprints and landscape disturbance at fine scales over time—an effort facilitated by remote sensing but still under development. Here, we report a satellite time-series analysis approach to detecting fine-scale human disturbances in an Ohio watershed dominated by forests and pastures but with diverse small-scale industrial activities such as hydraulic fracturing (HF) and surface mining. We leveraged Google Earth Engine to stack decades of Landsat images and explored the effectiveness of a fuzzy change detection algorithm called the Bayesian Estimator of Abrupt change, Seasonality, and Trend (BEAST) to capture fine-scale disturbances. BEAST is an ensemble method, capable of estimating changepoints probabilistically and identifying sub-pixel disturbances. We found the algorithm can successfully capture the patterns and timings of small-scale disturbances, such as grazing, agriculture management, coal mining, HF, and right-of-ways for gas and power lines, many of which were not captured in the annual land cover maps from Cropland Data Layers—one of the most widely used classification-based land dynamics products in the US. For example, BEAST could detect the initial HF wellpad construction within 60 days of the registered drilling dates on 88.2% of the sites. The wellpad footprints were small, disturbing only 0.24% of the watershed in area, which was dwarfed by other activities (e.g., right-of-ways of utility transmission lines). Together, these known activities have disturbed 9.7% of the watershed from the year 2000 to 2017 with evergeen forests being the most affected land cover. This study provides empirical evidence on the effectiveness and reliability of BEAST for changepoint detection as well as its capability to detect disturbances from satellite images at sub-pixel levels and also documents the value of Google Earth Engine and satellite time-series imaging for monitoring human activities in complex working landscapes.

Analysis and prediction of land cover changes using the land change modeler (LCM) in a semiarid river basin, Iran

AbstractPredicting future land cover (LC) changes is an important step in the proper planning and management of watersheds. As a susceptible area to salinity and desertification, receiving only about 195 mm rainfall annually, the Hable‐Rud River basin is especially sensitive to land use/cover changes. Based on corrected LANDSAT satellite images for the years 1986, 2000, and 2017, the LC were extracted using the maximum likelihood (ML) method. LC changes were predicted by applying the land change modeler (LCM) for the basin. The kappa index for classification in 1986, 2000, and 2017 was 75, 78, and 81%, respectively. Using LCM, the prediction was accomplished for the year 2017 with a kappa index of above 74%. The LC map was predicted for year 2040. The analysis indicates that over the past 32 years, bare land, saline land, agricultural, industrial, and residential areas have increased by about 8, 6.2, 2.7, 0.63, and 0.48%, respectively; while rangeland area was decreased by 18%. Results also indicate that given the predicted LC for year 2040 in comparison with the reference year (2017), saline land, agricultural, industrial, and residential areas will be likely to continue to increase by about 3, 1.5, 0.7, and 0.8%, respectively, whereas bare land and rangeland will most likely decrease by about 4.55 and 1.45%, respectively. The findings of this study assist in analyzing the future trends of LC changes in the basin. This information can be used as a guide for land planners and managers in future land use planning of the area.

Production of global daily seamless data cubes and quantification of global land cover change from 1985 to 2020 - iMap World 1.0

Longer time high-resolution, high-frequency, consistent, and more detailed land cover data are urgently needed in order to achieve sustainable development goals on food security, high-quality habitat construction, biodiversity conservation and planetary health, and for the understanding, simulation and management of the Earth system. However, due to technological constraints, it is difficult to provide simultaneously high spatial resolution, high temporal frequency, and high quality observation data. Existing mapping solutions are limited by traditional remotely sensed data, that have shorter observation periods, poor spatio-temporal consistency and comparability. Therefore, a new mapping paradigm is needed. This paper develops a framework for intelligent mapping (iMap) of land cover based on state-of-the-art technologies such as cloud computing, artificial intelligence, virtual constellations, and spatio-temporal reconstruction and fusion. Under this framework, we built an automated, serverless, end-to-end data production chain and parallel mapping system based on Amazon Web Services (AWS) and produced the first 30 m global daily seamless data cubes (SDC), and annual to seasonal land cover maps for 1985–2020. The SDC was produced through a multi-source spatio-temporal data reconstruction and fusion workflow based on Landsat, MODIS, and AVHRR virtual constellations. Independent validation results show that the relative mean error of the SDC is less than 2.14%. As analysis ready data (ARD), it can lay a foundation for high-precision quantitative remote sensing information extraction. From this SDC, we produced 36-year long, 30 m resolution global land cover map data set by combining strategies of sample migration, machine learning, and spatio-temporal adjustment. The average overall accuracy of our annual land cover maps over multiple periods of time is 80% for level 1 classification and over 73% for level 2 classification (29 and 33 classes). Based on an objective validation sample consisting of FLUXNET sites, our map accuracy is 10% higher than that of existing global land cover datasets including Globeland30. Our results show that the average global land cover change rate is 0.36%/yr. Global forest decreased by 1.47 million km2 from 38.44 million km2, cropland increased by 0.84 million km2 from 12.49 million km2 and impervious surface increased by 0.48 million km2 from 0.57 million km2 during 1985– 2020.

30 m annual land cover and its dynamics in China from 1990 to 2019

Abstract. Land cover (LC) determines the energy exchange, water and carbon cycle between Earth's spheres. Accurate LC information is a fundamental parameter for the environment and climate studies. Considering that the LC in China has been altered dramatically with the economic development in the past few decades, sequential and fine-scale LC monitoring is in urgent need. However, currently, fine-resolution annual LC dataset produced by the observational images is generally unavailable for China due to the lack of sufficient training samples and computational capabilities. To deal with this issue, we produced the first Landsat-derived annual China Land Cover Dataset (CLCD) on the Google Earth Engine (GEE) platform, which contains 30 m annual LC and its dynamics of China from 1990 to 2019. We first collected the training samples by combining stable samples extracted from China’s Land-Use/Cover Datasets (CLUD), and visually-interpreted samples from satellite time-series data, Google Earth and Google Map. Using 335,709 Landsat images on the GEE, several temporal metrics were constructed and fed to the random forest classifier to obtain classification results. We then proposed a post-processing method incorporating spatial-temporal filtering and logical reasoning to further improve the spatial-temporal consistency of CLCD. Finally, the overall accuracy of CLCD reached 79.31 % based on 5,463 visually-interpreted samples. A further assessment based on 5,131 third-party test samples showed that the overall accuracy of CLCD outperforms that of MCD12Q1, ESACCI_LC, FROM_GLC, and GlobaLand30. Besides, we intercompared the CLCD with several Landsat-derived thematic products, which exhibited good consistencies with the Global Forest Change, the Global Surface Water, and three impervious surface products. Based on the CLCD, the trends and patterns of China’s LC changes during 1985 and 2019 were revealed, such as expansion of impervious surface (+148.71 %) and water (+18.39 %), decrease of cropland (−4.85 %) and grassland (−3.29 %), increase of forest (+4.34 %). In general, CLCD reflected the rapid urbanization and a series of ecological projects (e.g., Gain for Green) in China and revealed the anthropogenic implications on LC under the condition of climate change, signifying its potential application in the global change research. The CLCD dataset introduced in this article is freely available at http://doi.org/10.5281/zenodo.4417810 (Yang and Huang, 2021).

21st century daily seamless data cube reconstruction and seasonal to annual land cover and land use dynamics mapping-iMap （China） 1.0

21st century daily seamless data cube reconstruction and seasonal to annual land cover and land use dynamics mapping-iMap （China） 1.0

Assessment of drought conditions over Vietnam using standardized precipitation evapotranspiration index, MERRA-2 re-analysis, and dynamic land cover

Study regionVietnam. Study focusIn recent years Vietnam has experienced historical drought events possibly affected by climate change, but the analysis is challenging due to lack of necessary observations for monitoring drought conditions. The goal of this study is to analyze the characteristics of droughts over a 30-year period, using three spatial-resolution MERRA-2 datasets in Vietnam. The Standardized Precipitation Evapotranspiration Index (SPEI) was used as an index for drought based on precipitation and temperature. We also estimated the impacts of drought on agriculture using annual land cover datasets. New hydrological insights for the regionsOur results identified significant increasing trends in precipitation in Northern Vietnam and decreasing trends in Southern Vietnam. The increasing trends in temperature occurred mainly in Southern Vietnam. These trends in rainfall and temperature resulted in an increasing trend in drought frequency and severity in Southern Vietnam, especially in the South-Central Region and the Mekong Delta. The comparison between the observed drought records and modeled drought index demonstrated that the simulated drought conditions are better at higher spatial resolution. The area under drought in agricultural lands calculated using dynamic land-cover data sets resulted in a better agreement with observed records. Our findings reveal the feasibility of using a model-based drought index in data-sparse areas for long-term trend drought analysis, and for practical applications of advanced re-analysis products in water resource management.

PASTURE LAND COVER CHANGE IN SÃO PAULO STATE, BRAZIL

Abstract. Pastures are complex land covers with a variety of land use systems. This land cover occupies large areas in the globe and is mainly used for livestock production. Brazil is one of the largest livestock producers and has extensive pasture areas. We analyzed the pasture land cover change of the São Paulo State between the years 2000 to 2015. São Paulo was chosen as study case due to its large industrial and agricultural importance and its expressive land cover changes over past decades. It was analyzed land covers databases generated by the Brazilian Annual Land Use and Land Cover Mapping Project (MapBiomas Project) – Collection 4. Transition matrix was generated to analyze the land cover change during the period. Gain, loss, total change, net change and swap were calculated in terms of area. Total pasture area decreased but continues the largest land cover of the São Paulo State; with 79.5% of persistence in the area. Main changes were from losses of pastures and gains in agriculture. Most of the changes to pasture came from other non vegetated areas and grassland categories. These results demonstrated the relevance of pastures areas in land cover change dynamics to address land use policy and plan future land use scenarios.

Improved Estimations of Nitrate and Sediment Concentrations Based on SWAT Simulations and Annual Updated Land Cover Products from a Deep Learning Classification Algorithm

The agricultural sector and natural resources are heavily interdependent, comprising a coherent but complex system. The soil and water assessment tool (SWAT) is widely used in assessing these interdependencies for regional watershed management. However, long-term simulations of agricultural watersheds are considered as not realistic since they have often been performed assuming constant land use over time and are based on the coarse resolution of the existing global or national data. This work presents the first insights of the synergy among SWAT model and deep learning classification algorithms to provide annually updated and realistic model’s parameterization and simulations. The proposed hybrid modelling approach couples the physical process SWAT model with the versatility of Earth observation data-driven non-linear deep learning algorithms for land use classification (Overall Accuracy (OA) = 79.58% and Kappa = 0.79), giving a strong advantage to decision makers for efficient management planning. A validation case at an agricultural watershed located in Northern Greece is provided to demonstrate their synergistic use to estimate nitrate and sediment concentrations that load in Zazari Lake. The SWAT model has been implemented under two different simulations; one with the use of a static coarse land use map and the other with the use of the annual updated land use maps for three consecutive years (2017–2019). The results indicate that the land use changes affect the final estimations resulting to an enhanced prediction performance of 1% and 2% for sediment and nitrate, respectively, when the annual land use maps are incorporated into SWAT simulations. In this context, a hybrid approach could further contribute to addressing challenges and support a data-centric scheme for informed decision making with regard to environmental and agricultural issues on the river basin scale.