Accuracy Assessment of Land Use/Land Cover Classification Using Remote Sensing and GIS

Remote sensing is one of the tool which is very important for the production of Land use and land cover maps through a process called image classification. For the image classification process to be successfully, several factors should be considered including availability of quality Landsat imagery and secondary data, a precise classification process and user’s experiences and expertise of the procedures. The objective of this research was to classify and map land-use/land-cover of the study area using remote sensing and Geospatial Information System (GIS) techniques. This research includes two sections (1) Landuse/Landcover (LULC) classification and (2) accuracy assessment. In this study supervised classification was performed using Non Parametric Rule. The major LULC classified were agriculture (65.0%), water body (4.0%), and built up areas (18.3%), mixed forest (5.2%), shrubs (7.0%), and Barren/bare land (0.5%). The study had an overall classification accuracy of 81.7% and kappa coefficient (K) of 0.722. The kappa coefficient is rated as substantial and hence the classified image found to be fit for further research. This study present essential source of information whereby planners and decision makers can use to sustainably plan the environment.

Assessing the Utility of Sentinel-1 C Band Synthetic Aperture Radar Imagery for Land Use Land Cover Classification in a Tropical Coastal Systems When Compared with Landsat 8

Cloud cover constitutes a major obstacle to land cover classification in the humid tropical regions when using optical remote sensing such as Landsat imagery. The advent of freely available Sentinel-1 C band synthetic aperture radar (SAR) imagery offers new opportunities for land cover classification in frequently cloud covered environments. In this study, we investigated the utility of Sentinel-1 for extracting land use land cover (LULC) information in the coastal low lying strip of Douala, Cameroon when compared with Landsat enhanced thematic mapper (TM). We also assessed the potential of integrating Sentinel-1 and Landsat. The major LULC classes in the region included water, settlement, bare ground, dark mangroves, green mangroves, swampy vegetation, rubber, coastal forest and other vegetation and palms. Textural variables including mean, correlation, contrast and entropy were derived from the Sentinel-1 C band. Various conventional image processing techniques and the support vector machine (SVM) algorithm were applied. Only four land cover classes (settlement, water, mangroves and other vegetation and rubber) could be calibrated and validated using SAR imagery due to speckles. The Sentinel-1 only classification yielded a lower overall classification accuracy (67.65% when compared to all Landsat bands (88.7%)). The integrated Sentinel-1 and Landsat data showed no significant differences in overall accuracy assessment (88.71% and 88.59%, respectively). The three best spectral bands (5, 6, 7) of Landsat imagery yielded the highest overall accuracy assessment (91.96%). in the study. These results demonstrate a lower potential of Sentinel-1 for land cover classification in the Douala estuary when compared with cloud free Landsat images. However, comparable results were obtained when only broad classes were considered.

Land use and cover change and influencing factor analysis in the Shiyang River Basin,China

Land use and cover change(LUCC)is the most direct manifestation of the interaction between anthropological activities and the natural environment on Earth's surface,with significant impacts on the environment and social economy.Rapid economic development and climate change have resulted in significant changes in land use and cover.The Shiyang River Basin,located in the eastern part of the Hexi Corridor in China,has undergone significant climate change and LUCC over the past few decades.In this study,we used the random forest classification to obtain the land use and cover datasets of the Shiyang River Basin in 1991,1995,2000,2005,2010,2015,and 2020 based on Landsat images.We validated the land use and cover data in 2015 from the random forest classification results(this study),the high-resolution dataset of annual global land cover from 2000 to 2015(AGLC-2000-2015),the global 30 m land cover classification with a fine classification system(GLC_FCS30),and the first Landsat-derived annual China Land Cover Dataset(CLCD)against ground-truth classification results to evaluate the accuracy of the classification results in this study.Furthermore,we explored and compared the spatiotemporal patterns of LUCC in the upper,middle,and lower reaches of the Shiyang River Basin over the past 30 years,and employed the random forest importance ranking method to analyze the influencing factors of LUCC based on natural(evapotranspiration,precipitation,temperature,and surface soil moisture)and anthropogenic(nighttime light,gross domestic product(GDP),and population)factors.The results indicated that the random forest classification results for land use and cover in the Shiyang River Basin in 2015 outperformed the AGLC-2000-2015,GLC_FCS30,and CLCD datasets in both overall and partial validations.Moreover,the classification results in this study exhibited a high level of agreement with the ground truth features.From 1991 to 2020,the area of bare land exhibited a decreasing trend,with changes primarily occurring in the middle and lower reaches of the basin.The area of grassland initially decreased and then increased,with changes occurring mainly in the upper and middle reaches of the basin.In contrast,the area of cropland initially increased and then decreased,with changes occurring in the middle and lower reaches.The LUCC was influenced by both natural and anthropogenic factors.Climatic factors and population contributed significantly to LUCC,and the importance values of evapotranspiration,precipitation,temperature,and population were 22.12%,32.41%,21.89%,and 19.65%,respectively.Moreover,policy interventions also played an important role.Land use and cover in the Shiyang River Basin exhibited fluctuating changes over the past 30 years,with the ecological environment improving in the last 10 years.This suggests that governance efforts in the study area have had some effects,and the government can continue to move in this direction in the future.The findings can provide crucial insights for related research and regional sustainable development in the Shiyang River Basin and other similar arid and semi-arid areas.

Comprehending drivers of land use land cover change from 1999 to 2021 in the Pithoragarh District,Kumaon Himalaya,Uttarakhand,India

The Himalayan region has been experiencing stark impacts of climate change,demographic and livelihood pattern changes.The analysis of land use and land cover(LULC)change provides insights into the shifts in spatial and temporal patterns of landscape.These changes are the combined effects of anthropogenic and natural/climatic factors.The present study attempts to monitor and comprehend the main drivers behind LULC changes(1999-2021)in the Himalayan region of Pithoragarh district,Uttarakhand.Pithoragarh district is a border district,remotely located in the north-east region of Uttarakhand,India.The study draws upon primary and secondary data sources.A total of 400 household surveys and five group discussions from 38 villages were conducted randomly to understand the climate perception of the local community and the drivers of change.Satellite imagery,CRU(Climatic Research Unit)climate data and climate perception data from the field have been used to comprehensively comprehend,analyze,and discuss the trends and reasons for LULC change.GIS and remote sensing techniques were used to construct LULC maps.This multifaceted approach ensures comprehensive and corroborated information.Five classes were identified and formed viz-cultivation,barren,settlement,snow,and vegetation.Results show that vegetation and builtup have increased whereas cultivation,barren land,and snow cover have decreased.The study further aims to elucidate the causes behind LULC changes in the spatially heterogeneous region,distinguishing between those attributed to human activities,climate shifts,and the interconnected impacts of both.The study provides a comprehensive picture of the study area and delivers a targeted understanding of local drivers and their potential remedies by offering a foundation for formulating sustainable adaptation policies in the region.

Spatiotemporal evolution and future simulation of land use/land cover in the Turpan-Hami Basin,China

The Turpan-Hami(Tuha)Basin in Xinjiang Uygur Autonomous Region of China,holds significant strategic importance as a key economic artery of the ancient Silk Road and the Belt and Road Initiative,necessitating a holistic understanding of the spatiotemporal evolution of land use/land cover(LULC)to foster sustainable planning that is tailored to the region's unique resource endowments.However,existing LULC classification methods demonstrate inadequate accuracy,hindering effective regional planning.In this study,we established a two-level LULC classification system(8 primary types and 22 secondary types)for the Tuha Basin.By employing Landsat 5/7/8 imagery at 5-a intervals,we developed the LULC dataset of the Tuha Basin from 1990 to 2020,conducted the accuracy assessment and spatiotemporal evolution analysis,and simulated the future LULC under various scenarios via the Markov-Future Land Use Simulation(Markov-FLUS)model.The results revealed that the average overall accuracy values of our LULC dataset were 0.917 and 0.864 for the primary types and secondary types,respectively.Compared with the seven mainstream LULC products(GlobeLand30,Global 30-meter Land Cover with Fine Classification System(GLC_FCS30),Finer Resolution Observation and Monitoring of Global Land Cover PLUS(FROM_GLC PLUS),ESA Global Land Cover(ESA_LC),Esri Land Cover(ESRI_LC),China Multi-Period Land Use Land Cover Change Remote Sensing Monitoring Dataset(CNLUCC),and China Annual Land Cover Dataset(CLCD))in 2020,our LULC data exhibited dramatically elevated overall accuracy and provided more precise delineations for land features,thereby yielding high-quality data backups for land resource analyses within the basin.In 2020,unused land(78.0%of the study area)and grassland(18.6%)were the dominant LULC types of the basin;although cropland and construction land constituted less than 1.0%of the total area,they played a vital role in arid land development and primarily situated within oases that form the urban cores of the cities of Turpan and Hami.Between 1990 and 2020,cropland and construction land exhibited a rapid expansion,and the total area of water body decreased yet resurging after 2015 due to an increase in areas of reservoir and pond.In future scenario simulations,significant increases in areas of construction land and cropland are anticipated under the business-as-usual scenario,whereas the wetland area will decrease,suggesting the need for ecological attention under this development pathway.In contrast,the economic development scenario underscores the fast-paced expansion of construction land,primarily from the conversion of unused land,highlighting the significant developmental potential of unused land with a slowing increase in cropland.Special attention should thus be directed toward ecological and cropland protection during development.This study provides data supports and policy recommendations for the sustainable development goals of Tuha Basin and other similar arid areas.

Dynamics of Land Use/Land Cover Considering Ecosystem Services for a Dense-Population Watershed Based on a Hybrid Dual-Subject Agent and Cellular Automaton Modeling Approach

Land use/land cover represents the interactive and comprehensive influences between human activities and natural conditions,leading to potential conflicts among natural and human-related issues as well as among stakeholders.This study introduced economic standards for farmers.A hybrid approach(CA-ABM)of cellular automaton(CA)and an agent-based model(ABM)was developed to effectively deal with social and land-use synergic issues to examine human–environment interactions and projections of land-use conversions for a humid basin in south China.Natural attributes and socioeconomic data were used to analyze land use/land cover and its drivers of change.The major modules of the CA-ABM are initialization,migration,assets,land suitability,and land-use change decisions.Empirical estimates of the factors influencing the urban land-use conversion probability were captured using parameters based on a spatial logistic regression(SLR)model.Simultaneously,multicriteria evaluation(MCE)and Markov models were introduced to obtain empirical estimates of the factors affecting the probability of ecological land conversion.An agent-based CA-SLR-MCE-Markov(ABCSMM)land-use conversion model was proposed to explore the impacts of policies on land-use conversion.This model can reproduce observed land-use patterns and provide links for forest transition and urban expansion to land-use decisions and ecosystem services.The results demonstrated land-use simulations under multi-policy scenarios,revealing the usefulness of the model for normative research on land-use management.

Spatiotemporal characteristics and driving mechanisms of land use/land cover(LULC)changes in the Jinghe River Basin,China

Understanding the trajectories and driving mechanisms behind land use/land cover(LULC)changes is essential for effective watershed planning and management.This study quantified the net change,exchange,total change,and transfer rate of LULC in the Jinghe River Basin(JRB),China using LULC data from 2000 to 2020.Through trajectory analysis,knowledge maps,chord diagrams,and standard deviation ellipse method,we examined the spatiotemporal characteristics of LULC changes.We further established an index system encompassing natural factors(digital elevation model(DEM),slope,aspect,and curvature),socio-economic factors(gross domestic product(GDP)and population),and accessibility factors(distance from railways,distance from highways,distance from water,and distance from residents)to investigate the driving mechanisms of LULC changes using factor detector and interaction detector in the geographical detector(Geodetector).The key findings indicate that from 2000 to 2020,the JRB experienced significant LULC changes,particularly for farmland,forest,and grassland.During the study period,LULC change trajectories were categorized into stable,early-stage,late-stage,repeated,and continuous change types.Besides the stable change type,the late-stage change type predominated the LULC change trajectories,comprising 83.31% of the total change area.The period 2010-2020 witnessed more active LULC changes compared to the period 2000-2010.The LULC changes exhibited a discrete spatial expansion trend during 2000-2020,predominantly extending from southeast to northwest of the JRB.Influential driving factors on LULC changes included slope,GDP,and distance from highways.The interaction detection results imply either bilinear or nonlinear enhancement for any two driving factors impacting the LULC changes from 2000 to 2020.This comprehensive understanding of the spatiotemporal characteristics and driving mechanisms of LULC changes offers valuable insights for the planning and sustainable management of LULC in the JRB.

Riparian habitat quality as an indicator of land use/land cover effects on riverine water quality

Riparian land use/land cover(LULC)plays a crucial role in maintaining riverine water quality by altering the transport of pollutants and nutrients.Nevertheless,establishing a direct relationship between water quality and LULC is challenging due to the multi-indicator nature of both factors.Water quality encompasses a multitude of physical,chemical,and biological parameters,while LULC represents a diverse array of land use types.Riparian habitat quality(RHQ)serves as an indicator of LULC.Yet,it remains to be seen whether RHQ can act as a proxy of LULC for assessing the impact of LULC on riverine water quality.This study examines the interplay between RHQ,LULC and water quality,and develops a comprehensive indicator to predict water quality.We measured several water quality parameters,including pH(potential of hydrogen),TN(total nitrogen),TP(total phosphorus),T_(water)(water temperature),DO(dissolved oxygen),and EC(electrical conductivity)of the Yue and Jinshui Rivers draining to the Han River during 2016,2017 and 2018.The water quality index(WQI)was further calculated.RHQ is assessed by the InVEST(Integrated Valuation of Ecosystem Services and Tradeoffs)model.Our study found noticeable seasonal differences in water quality,with a higher WQI observed in the dry season.The RHQ was strongly correlated with LULC compositions.RHQ positively correlated with WQI,and DO concentration and vegetation land were negatively correlated with T_(water),TN,TP,EC,cropland,and construction land.These correlations were stronger in the rainy season.Human-dominated land,such as construction land and cropland,significantly contributed to water quality degradation,whereas vegetation promoted water quality.Regression models showed that the RHQ explained variations in WQI better than LULC types.Our study concludes that RHQ is a new and comprehensive indicator for predicting the dynamics of riverine water quality.

Spatiotemporal dynamics of land use/land cover(LULC)changes and its impact on land surface temperature:A case study in New Town Kolkata,eastern India

Rapid urbanization creates complexity,results in dynamic changes in land and environment,and influences the land surface temperature(LST)in fast-developing cities.In this study,we examined the impact of land use/land cover(LULC)changes on LST and determined the intensity of urban heat island(UHI)in New Town Kolkata(a smart city),eastern India,from 1991 to 2021 at 10-a intervals using various series of Landsat multi-spectral and thermal bands.This study used the maximum likelihood algorithm for image classification and other methods like the correlation analysis and hotspot analysis(Getis–Ord Gi^(*) method)to examine the impact of LULC changes on urban thermal environment.This study noticed that the area percentage of built-up land increased rapidly from 21.91%to 45.63%during 1991–2021,with a maximum positive change in built-up land and a maximum negative change in sparse vegetation.The mean temperature significantly increased during the study period(1991–2021),from 16.31℃to 22.48℃in winter,29.18℃to 34.61℃in summer,and 19.18℃to 27.11℃in autumn.The result showed that impervious surfaces contribute to higher LST,whereas vegetation helps decrease it.Poor ecological status has been found in built-up land,and excellent ecological status has been found in vegetation and water body.The hot spot and cold spot areas shifted their locations every decade due to random LULC changes.Even after New Town Kolkata became a smart city,high LST has been observed.Overall,this study indicated that urbanization and changes in LULC patterns can influence the urban thermal environment,and appropriate planning is needed to reduce LST.This study can help policy-makers create sustainable smart cities.

The Review of Land Use/Land Cover Mapping AI Methodology and Application in the Era of Remote Sensing Big Data

With the increasing number of remote sensing satellites,the diversification of observation modals,and the continuous advancement of artificial intelligence algorithms,historically opportunities have been brought to the applications of earth observation and information retrieval,including climate change monitoring,natural resource investigation,ecological environment protection,and territorial space planning.Over the past decade,artificial intelligence technology represented by deep learning has made significant contributions to the field of Earth observation.Therefore,this review will focus on the bottlenecks and development process of using deep learning methods for land use/land cover mapping of the Earth’s surface.Firstly,it introduces the basic framework of semantic segmentation network models for land use/land cover mapping.Then,we summarize the development of semantic segmentation models in geographical field,focusing on spatial and semantic feature extraction,context relationship perception,multi-scale effects modelling,and the transferability of models under geographical differences.Then,the application of semantic segmentation models in agricultural management,building boundary extraction,single tree segmentation and inter-species classification are reviewed.Finally,we discuss the future development prospects of deep learning technology in the context of remote sensing big data.

Characteristics and drivers of the soil multifunctionality under different land use and land cover types in the drylands of China

The drylands of China cover approximately 6.6×106 km2 and are home to approximately 5.8×10^(8)people,providing important ecosystem services for human survival and development.However,dryland ecosystems are extremely fragile and sensitive to external environmental changes.Land use and land cover(LULC)changes significantly impact soil structure and function,thus affecting the soil multifunctionality(SMF).However,the effect of LULC changes on the SMF in the drylands of China has rarely been reported.In this study,we investigated the characteristics of the SMF changes based on soil data in the 1980s from the National Tibetan Plateau Data Center.We explored the drivers of the SMF changes under different LULC types(including forest,grassland,shrubland,and desert)and used structural equation modeling to explore the main driver of the SMF changes.The results showed that the SMF under the four LULC types decreased in the following descending order:forest,grassland,shrubland,and desert.The main driver of the SMF changes under different LULC types was mean annual temperature(MAT).In addition to MAT,pH in forest,soil moisture(SM)and soil biodiversity index in grassland,SM in shrubland,and aridity index in desert are crucial factors for the SMF changes.Therefore,the SMF in the drylands of China is regulated mainly by MAT and pH,and comprehensive assessments of the SMF in drylands need to be performed regarding LULC changes.The results are beneficial for evaluating the SMF among different LULC types and predicting the SMF under global climate change.

An Analysis of Land Use and Land Cover Changes, and Implications for Conservation in Mukumbura (Ward 2), Mt Darwin, Zimbabwe, 2002-2022

Understanding trends of land use land cover (LULC) changes is important for biodiversity monitoring and conservation planning, and identifying the areas affected by change and designing sustainable solutions to reduce the changes. The study aims to evaluate and quantify the historical changes in land use and land cover in Mukumbura (Ward 2), Mt Darwin, Zimbabwe, from 2002 to 2022. The objective of the study was to analyse the LULC changes in Ward 2 (Mukumbura), Mt Darwin, Northern Zimbabwe, for a period of 20 years using geospatial techniques. Landsat satellite images were processed using Google Earth Engine (GEE) and the supervised classification with maximum likelihood algorithm was employed to generate LULC maps between 2002 and 2022 with a five (5) year interval, investigating the following variables, forest cover, barren land, water cover and the fields. Findings revealed a substantial reduction in forest cover by 38.8%, water bodies (wetlands, ponds, and rivers) declined by 55.6%, whilst fields (crop/agricultural fields) increased by 93.3% and the barren land cover increased by 26.3% from 2002 to 2022. These findings point to substantial changes in LULC over the observed years. LULC changes have resulted in habitat fragmentation, reduced biodiversity, and the disruption of ecosystem functions. The study concludes that if these deforestation trends, cultivation, and settlement land expansion continue, the ward will have limited indigenous fruit trees. Therefore, the causes for LULC changes must be controlled, sustainable forest resources use practiced, hence the need to domesticate the indigenous fruit trees in arborloo toilets.

Land Use Land Cover Analysis for Godavari Basin in Maharashtra Using Geographical Information System and Remote Sensing

The dynamic transformation of land use and land cover has emerged as a crucial aspect in the effective management of natural resources and the continual monitoring of environmental shifts. This study focused on the land use and land cover (LULC) changes within the catchment area of the Godavari River, assessing the repercussions of land and water resource exploitation. Utilizing LANDSAT satellite images from 2009, 2014, and 2019, this research employed supervised classification through the Quantum Geographic Information System (QGIS) software’s SCP plugin. Maximum likelihood classification algorithm was used for the assessment of supervised land use classification. Seven distinct LULC classes—forest, irrigated cropland, agricultural land (fallow), barren land, shrub land, water, and urban land—are delineated for classification purposes. The study revealed substantial changes in the Godavari basin’s land use patterns over the ten-year period from 2009 to 2019. Spatial and temporal dynamics of land use/cover changes (2009-2019) were quantified using three Satellite/Landsat images, a supervised classification algorithm and the post classification change detection technique in GIS. The total study area of the Godavari basin in Maharashtra encompasses 5138175.48 hectares. Notably, the built-up area increased from 0.14% in 2009 to 1.94% in 2019. The proportion of irrigated cropland, which was 62.32% in 2009, declined to 41.52% in 2019. Shrub land witnessed a noteworthy increase from 0.05% to 2.05% over the last decade. The key findings underscored significant declines in barren land, agricultural land, and irrigated cropland, juxtaposed with an expansion in forest land, shrub land, and urban land. The classification methodology achieved an overall accuracy of 80%, with a Kappa Statistic of 71.9% for the satellite images. The overall classification accuracy along with the Kappa value for 2009, 2014 and 2019 supervised land use land cover classification was good enough to detect the changing scenarios of Godavari River basin under study. These findings provide valuable insights for discerning land utilization across various categories, facilitating the adoption of appropriate strategies for sustainable land use in the region.

Land Use and Land Cover Dynamics in the Eseka Alluvial Gold Mining District, Centre Region, Cameroon

Local populations in Cameroon thrive on forest resources and the flow of ecosystem services they provide are pivotal in sustaining national economy, improving people’s lives, safeguarding biodiversity, and mitigating the impacts of environmental changes. The exploitation of these resources invariably leads to deforestation and forest degradation. This study was designed to evaluate land use land cover change (LULCC) in the Eseka alluvial gold mining district with the aid of Landsat images. In the investigation of forest cover change, four Landsat satellite images for (1990, 2002, 2015 and 2022) were used. Ground-truthing also helped to identify the activities carried out by the local population and to determine agents, drivers and pressures of land use and land cover change. Four main land cover classes namely: forest, agricultural land, settlement/mining camps and water bodies were selected. Between 1990 and 2022, the proportion of forest decreased from 98% to 34% while those of agricultural land and settlement/mining camps increased from 2% to 60% and 0.54% to 6% respectively. Analysis showed ongoing deforestation with forest cover loss of ~98,263 ha in 32 years giving a cover change percentage of 63.94%. Kappa coefficient for the study period ranged from 0.92 to 0.99. Forest cover loss could be attributed to farming activities, wood extraction and alluvial gold mining activities. Economic motives notably the need to increase household income from a frequent demand for farm and wood products in neighbouring towns and the quest for gold were the main drivers of these activities. Hence, this study assesses the impact of human activities from the mining sector on the forest ecosystem in a bid to inform mitigation policies.

Trends of Land Use and Land Cover Change in the Savannah Ecological of the Protected Area Reserve Partielle de Dosso, Niger

Information on the dynamics of savannah is important to a country's plan to overcome the problems of uncontrolled development and environmental hazards. Taking the reserve partielle de Dosso, Niger as the case study area, this paper analyzed the long-term land use land cover change from 2002 to 2022. Satellite images were processed by using Google Earth Engine (GEE). Therefore, four major land cover classes were identified based on spectral characteristics of Land sat, namely, built-up, vegetation, cropland, bare land and water. The result revealed that barren and built-up areas increased at the expense of vegetation and water. From the four major land use land cover the large area is covered by vegetation which comprises about 192963.5 hectares followed by cropland and water consisting of 32506.43 and 1596.4 hectares respectively. The built-up area gained substantial area (most) during the study period. The reduction in some of the land cover/uses underlines the dangerous trend of the pressure poised by population growth and the changing functionality. Land cover change is influenced by a variety of societal factors operating on several spatial and temporal levels. The area estimates and spatial distributions of the LULC classes produced from the current study will assist local authorities, managers, and other stakeholders in decision-making and planning regarding forest land cover and uses.

Assessment of the cropland classifications in four global land cover datasets： A case study of Shaanxi Province, China

Accurate and reliable cropland surface information is of vital importance for agricultural planning and food security monitoring. As several global land cover datasets have been independently released, an inter-comparison of these data products on the classification of cropland is highly needed. This paper presents an assessment of cropland classifications in four global land cover datasets, i.e., moderate resolution imaging spectrometer （MODIS） land cover product, global land cover map of 2009 （GlobCover2009）, finer resolution observation and monitoring of global cropland （FROM-GC） and 30-m global land cover dataset （GlobeLand30）. The temporal coverage of these four datasets are circa 2010. One of the typical agricultur- al regions of China, Shaanxi Province, was selected as the study area. The assessment proceeded from three aspects： accuracy, spatial agreement and absolute area. In accuracy assessment, 506 validation samples, which consist of 168 cropland samples and 338 non-cropland ones, were automatically and systematically selected, and manually interpreted by referencing high-resolution images dated from 2009 to 2011 on Google Earth. The results show that the overall accuracy （OA） of four datasets ranges from 61.26 to 80.63%. GlobeLand30 dataset, with the highest accuracy, is the most accurate dataset for cropland classification. The cropland spatial agreement （mainly located in the plain ecotope of Shaanxi） and the non-cropland spatial agreement （sparsely distributed in the south and middle of Shaanxi） of the four datasets only makes up 33.96% of the whole province. FIROM-GC and GlobeLand30, obtaining the highest spatial agreement index of 62.40%, have the highest degree of spatial consistency. In terms of the absolute area, MODIS underestimates the cropland area, while GlobCover2009 significantly overestimates it. These findings are of value in revealing to which extent and on which aspect that these global land cover datasets may agree with each other at small scale on each ecotope region. The approaches taken in this study could be used to derive a fused cropland classification dataset.

Integrating TM and Ancillary Geographical Data with Classification Trees for Land Cover Classification of Marsh Area

The main objective of this research is to determine the capacity of land cover classification combining spec- tral and textural features of Landsat TM imagery with ancillary geographical data in wetlands of the Sanjiang Plain, Heilongjiang Province, China. Semi-variograms and Z-test value were calculated to assess the separability of grey-level co-occurrence texture measures to maximize the difference between land cover types. The degree of spatial autocorrelation showed that window sizes of 3×3 pixels and 11×11 pixels were most appropriate for Landsat TM im- age texture calculations. The texture analysis showed that co-occurrence entropy, dissimilarity, and variance texture measures, derived from the Landsat TM spectrum bands and vegetation indices provided the most significant statistical differentiation between land cover types. Subsequently, a Classification and Regression Tree (CART) algorithm was applied to three different combinations of predictors: 1) TM imagery alone (TM-only); 2) TM imagery plus image texture (TM+TXT model); and 3) all predictors including TM imagery, image texture and additional ancillary GIS in- formation (TM+TXT+GIS model). Compared with traditional Maximum Likelihood Classification (MLC) supervised classification, three classification trees predictive models reduced the overall error rate significantly. Image texture measures and ancillary geographical variables depressed the speckle noise effectively and reduced classification error rate of marsh obviously. For classification trees model making use of all available predictors, omission error rate was 12.90% and commission error rate was 10.99% for marsh. The developed method is portable, relatively easy to im- plement and should be applicable in other settings and over larger extents.

Effects of RapidEye Imagery's Red-edge Band and Vegetation Indices on Land Cover Classification in an Arid Region

Land cover classification(LCC) in arid regions is of great significance to the assessment, prediction, and management of land desertification. Some studies have shown that the red-edge band of RapidE ye images was effective for vegetation identification and could improve LCC accuracy. However, there has been no investigation of the effects of RapidE ye images' red-edge band and vegetation indices on LCC in arid regions where there are spectrally similar land covers mixed with very high or low vegetation coverage information and bare land. This study focused on a typical inland arid desert region located in Dunhuang Basin of northwestern China. First, five feature sets including or excluding the red-edge band and vegetation indices were constructed. Then, a land cover classification system involving plant communities was developed. Finally, random forest algorithm-based models with different feature sets were utilized for LCC. The conclusions drawn were as follows: 1) the red-edge band showed slight contribution to LCC accuracy; 2) vegetation indices had a significant positive effect on LCC; 3) simultaneous addition of the red-edge band and vegetation indices achieved a significant overall accuracy improvement(3.46% from 86.67%). In general, vegetation indices had larger effect than the red-edge band, and simultaneous addition of them significantly increased the accuracy of LCC in arid regions.

Evaluation of a deep-learning model for multispectral remote sensing of land use and crop classification

High-resolution deep-learning-based remote-sensing imagery analysis has been widely used in land-use and crop-classification mapping. However, the influence of composite feature bands, including complex feature indices arising from different sensors on the backbone, patch size, and predictions in transferable deep models require further testing. The experiments were conducted in six sites in Henan province from2019 to 2021. This study sought to enable the transfer of classification models across regions and years for Sentinel-2 A(10-m resolution) and Gaofen PMS(2-m resolution) imagery. With feature selection and up-sampling of small samples, the performance of UNet++ architecture on five backbones and four patch sizes was examined. Joint loss, mean Intersection over Union(m Io U), and epoch time were analyzed, and the optimal backbone and patch size for both sensors were Timm-Reg Net Y-320 and 256 × 256, respectively. The overall accuracy and Fscores of the Sentinel-2 A predictions ranged from 96.86% to 97.72%and 71.29% to 80.75%, respectively, compared to 75.34%–97.72% and 54.89%–73.25% for the Gaofen predictions. The accuracies of each site indicated that patch size exerted a greater influence on model performance than the backbone. The feature-selection-based predictions with UNet++ architecture and upsampling of minor classes demonstrated the capabilities of deep-learning generalization for classifying complex ground objects, offering improved performance compared to the UNet, Deeplab V3+, Random Forest, and Object-Oriented Classification models. In addition to the overall accuracy, confusion matrices,precision, recall, and F1 scores should be evaluated for minor land-cover types. This study contributes to large-scale, dynamic, and near-real-time land-use and crop mapping by integrating deep learning and multi-source remote-sensing imagery.

Land Cover Classification with Multi-source Data Using Evidential Reasoning Approach

Land cover classification is the core of converting satellite imagery to available geographic data.However,spectral signatures do not always provide enough information in classification decisions.Thus,the application of multi-source data becomes necessary.This paper presents an evidential reasoning (ER) approach to incorporate Landsat TM imagery,altitude and slope data.Results show that multi-source data contribute to the classification accuracy achieved by the ER method,whereas play a negative role to that derived by maximum likelihood classifier (MLC).In comparison to the results derived based on TM imagery alone,the overall accuracy rate of the ER method increases by 7.66% and that of the MLC method decreases by 8.35% when all data sources (TM plus altitude and slope) are accessible.The ER method is regarded as a better approach for multi-source image classification.In addition,the method produces not only an accurate classification result,but also the uncertainty which presents the inherent difficulty in classification decisions.The uncertainty associated to the ER classification image is evaluated and proved to be useful for improved classification accuracy.