Effects of machine learning models and spatial resolution on land cover classification accuracy in Dali County, Shaanxi, China
Abstract
comparing the differences between four machine learning algorithms for LULC mapping. The classification results of this model were also compared with existing global land cover datasets to determine whether the model was capable of producing reliable results. According to the results of this study, the random forest (RF) classifier outperformed the support vector machine (SVM), decision tree (DT), and artificial neural network (ANN) with an overall accuracy (OA) and kappa coefficient of 81.99% and 0.78, respectively. However, SVM and ANN showed greater accuracy on the water class and unused land class, respectively. With increasing spatial resolution, RF’s accuracy increased initially and then decreased when classifying images
with five different spatial resolutions (30 m, 16 m, 10 m, 8 m, and 2 m). In particular, with an OA of 82.54% and a kappa coefficient of 0.78, RF performed the best on images with 8 m resolution. Additionally, the RF-based image with 8 m resolution produced a higher OA of 0.88 for cropland. Topography is the main factor that determines the classification performance of different-resolution images. The classification accuracies of RF10 m and RF30 m (10 m and 30 m resolution images, respectively, using RF) were higher (OAs of 93.59% and 94.59%, respectively) than those of the global land cover dataset (LC10 m and LC30 m, land cover images with 10 m and 30 m resolution, respectively), whose high-resolution images showed more details of the land cover. The results of this study highlight that classification algorithms and image resolution are the sources of uncertainty for land mapping. Obtaining reliable land cover mapping requires the use of appropriate classification algorithms and spatial resolution. With these results, it will be possible to develop a national land monitoring system and basic ecological climate models using LULC.
Keywords: satellite data, different spatial resolutions, machine learning, land use, land cover, random forest, uncertainty
DOI: 10.25165/j.ijabe.20251801.7252
Citation: Shi Y, Jin N, Wu B Y, Wang Z K, Wang S W, Yu Q. Effects of machine learning models and spatial resolution on land cover classification accuracy in Dali County, Shaanxi, China. Int J Agric & Biol Eng, 2025; 18(1): 245–259.
Keywords
Full Text:
PDFReferences
Sun D, Zhang W X, Lin Y B, Liu Z F, Shen W J, Zhou L X, et al. Soil erosion and water retention varies with plantation type and age. Forest Ecology and Management, 2018; 422: 1–10.
Lin D L, Xia J Y, Wan S Q. Climate warming and biomass accumulation of terrestrial plants: A meta-analysis. New Phytologist, 2010; 188(1): 187–198.
Liang J Y, Xia J Y, Liu L L, Wang S Q. Global patterns of the responses of leaf-level photosynthesis and respiration in terrestrial plants to experimental warming. Journal of Plant Ecology, 2013; 6(6): 437–447.
Geist H, Lambin E F (Eds.). Land-use and land-cover change: Local processes to global impacts. Springer, 2006; 205p.
Bussi G, Whitehead P G, Gutierrz-Canovas C, Ledesma J L J, Ormerod S J, Counture R M. Modelling the effects of climate and land-use change on the hydrochemistry and ecology of the River Wye (Wales). Science of The Total Environment, 2018; 627: 733–743.
Luo Z L, Shao Q X, Zuo Q T, Cui Y K. Impact of land use and urbanization on river water quality and ecology in a dam dominated basin. Journal of Hydrology, 2020; 584: 124655.
Sun Z H, Di L P, Fang H, Burgess A. Deep learning classification for crop types in North Dakota. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020; 13: 2200–2213.
Zhang C, Di L P, Lin L, Guo L Y. Machine-learned prediction of annual crop planting in the U.S. Corn Belt based on historical crop planting maps. Computers and Electronics in Agriculture, 2019; 166: 104989.
Fritz S, See L, Rembold F. Comparison of global and regional land cover maps with statistical information for the agricultural domain in Africa. International Journal of Remote Sensing, 2010; 31(9): 2237–2256.
Pu R L, Bell S. Mapping seagrass coverage and spatial patterns with high spatial resolution IKONOS imagery. International Journal of Applied Earth Observation and Geoinformation, 2017; 54: 145–158.
Hansen M C, Potapov P V, Moore R, Hancher M, Turubanova S A, Tyukavina A, et al. High-resolution global maps of 21st-century forest cover change. Science, 2013; 342(6160): 850–853.
Wang C, Tandeo P, Mouche A, Stopa J E, Gressani V, Longepe N, et al. Classification of the global Sentinel-1 SAR vignettes for ocean surface process studies. Remote Sensing of Environment, 2019; 234: 111457.
do Nascimento Bendini H, Fonseca L M G, Schwieder M, Korting T S, Rufin P, Del Arco Sanches I, et al. Detailed agricultural land classification in the Brazilian cerrado based on phenological information from dense satellite image time series. International Journal of Applied Earth Observation And Geoinformation, 2019; 82: 101872.
Preidl S, Lange M, Doktor D. Introducing APiC for regionalised land cover mapping on the national scale using Sentinel-2A imagery. Remote Sensing of Environment, 2020; 240: 111673.
Lu D, Weng Q. A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing, 2007; 28(5): 823–870.
Lyu Z Y, He H Q, Benediktsson J A, Huang H. A generalized image scene decomposition-based system for supervised classification of very high resolution remote sensing imagery. Remote Sensing, 2016; 8(10): 814. doi: A generalized image scene decomposition-based system for supervised classification of very high resolution remote sensing imagery.
Wang J, Xiao X M, Liu L, Wu X C, Qin Y W, Steiner J L, et al. Mapping sugarcane plantation dynamics in Guangxi, China, by time series Sentinel-1, Sentinel-2 and Landsat images. Remote Sensing of Environment, 2020; 247: 111951.
Zhong Y F, Su Y, Wu S Q, Zheng Z D, Zhao J, Ma A L, et al. Open-source data-driven urban land-use mapping integrating point-line-polygon semantic objects: A case study of Chinese cities. Remote Sensing of Environment, 2020; 247: 111838.
Hu T Y, Yang J, Li X C, Gong P. Mapping urban land use by using Landsat images and open social data. Remote Sensing, 2016; 8(2): 151.
Sharma R C, Tateishi R, Hara K, Iizuka K. Production of the Japan 30-m land cover map of 2013-2015 using a random forests-based feature optimization approach. Remote Sensing, 2016; 8(5): 429.
Gómez C, White J C, Wulder M A. Optical remotely sensed time series data for land cover classification: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 2016; 116: 55–72.
Shi Y, Li L C, Wu B Y, Zhang Y J, Wang B, Niu W H, et al. Predicting rice productivity for ground data-sparse regions: A transferable framework and its application to North Korea. Science of The Total Environment, 2024; 946: 174227.
Cortes C, Vapnik V. Support-vector networks. Machine Learning, 1995; 20(3): 273–297.
Shi Y, Jin N, Ma X L, Wu B Y, He Q S, Yue C, et al. Attribution of climate and human activities to vegetation change in China using machine learning techniques. Agricultural and Forest Meteorology, 2020; 294: 108146.
Pal M, Mather P M. Support vector machines for classification in remote sensing. International Journal of Remote Sensing, 2006; 26(5): 1007–1011.
Schneider A. Monitoring land cover change in urban and peri-urban areas using dense time stacks of Landsat satellite data and a data mining approach. Remote Sensing of Environment, 2012; 124: 689–704.
Hackman K O, Gong P, Wang, J. New land-cover maps of Ghana for 2015 using Landsat 8 and three popular classifiers for biodiversity assessment. International Journal of Remote Sensing, 2017; 38(14): 4008–4021.
Maxwell A E, Warner T A, Fang F. Implementation of machine-learning classification in remote sensing: an applied review. International Journal of Remote Sensing, 2018; 39(9): 2784–2817.
Biradar C M, Thenkabail P S, Noojipady P, Li Y J, Dheeravath V, Turral H, et al. A global map of rainfed cropland areas (GMRCA) at the end of last millenium using remote sensing. International Journal of Applied Earth Observation and Geoinformation, 2009; 11(2): 114–129.
Thenkabail P S, Birandar C M, Noojipady P. Global irrigated area map (GIAM), derived from remote sensing, for the end of the last millennium. International Journal of Remote Sensing, 2009; 30(14): 3679–3733.
Ramankutty N, Evan A T, Monfreda C, Foley J A. Farming the planet: 1. Geographic distribution of global agricultural lands in the year 2000. Global Biogeochemical Cycles, 2008; 22(1): GB1003.
Vancutsem C, Marinho E, Kayitakire F, See L, Fritz S. Harmonizing and combining existing land Cover/Land use datasets for cropland area monitoring at the African continental scale. Remote Sensing, 2013; 5(1): 19–41.
Chen J, Chen J, Liao A P, Cao X, Chen L J, Chen X H, et al. Global land cover mapping at 30m resolution: A POK-based operational approach. ISPRS Journal of Photogrammetry and Remote Sensing, 2015; 103: 7–27.
Pérez-Hoyos A, Rembold F, Kerdiles H, Gallego J. Comparison of global land cover datasets for cropland monitoring. Remote Sensing, 2017; 9(11): 1118.
Feng X M, Fu B J, Piao S L, Wang S, Ciais P, Zeng Z Z, et al. Revegetation in China’s Loess Plateau is approaching sustainable water resource limits. Nature Climate Change, 2016; 6(11): 1019–1022.
Gong P, Li X C, Zhang W. 40-Year (1978-2017) human settlement changes in China reflected by impervious surfaces from satellite remote sensing. Science Bulletin, 2019; 64(11): 756–763.
U. S. Geological Survey. Landsat-Earth observation satellites (ver. 1.2, April 2020): U. S. Geological Survey Fact Sheet 2015-3081, 2016; 4p.
Adler-Golden S, Matthew M W, Bernstein L S, Levine R Y, Berk A, Richtsmeier S C, et al. Atmospheric correction for shortwave spectral imagery based on MODTRAN4. In: Proceedings of SPIE - International Symposium on Optical Science, Engineering and Instrumentation, 1999; 3753: 366315. doi: 10.1117/12.366315.
European Space Agency. Sentinel-2 User Handbook, 2015. Available: https:// sentinel.esa.int/web/sentinel/user-guides. Accessed on [2024-02-24].
Clevers J G P W, Kooistra L. Using hyperspectral remote sensing data for retrieving canopy chlorophyll and nitrogen content. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012; 5(2): 574–583.
Yang N, Li J H, Mo W B, Luo W J, Wu D, Gao W C, et al. Water depth retrieval models of East Dongting Lake, China, using GF-1 multi-spectral remote sensing images. Global Ecology and Conservation, 2020; 22: e01004.
Laben C A, Brower B V. Process for enhancing the spatial resolution of multispectral imagery using pan-sharpening. US, 2000; Patent notice No. US06011875A.
Daughtry C S T, Walthall C L, Kim M S, de Colstoun E B, McMurtrey J E Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance. Remote Sensing of Environment, 2000; 74: 229–239.
Nicolaï B M, Beullens K, Bobelyn E, Peirs A, Saeys W, Theron K I, et al. Nondestructive measurement of fruit and vegetable quality by means of NIR spectroscopy: A review. Postharvest Biology and Technology, 2007; 46: 99–118.
Yue L W, Shen H F, Zhang L P, Zheng X W, Zhang F, Yuan Q Q. High-quality seamless DEM generation blending SRTM-1, ASTER GDEM v2 and ICESat/GLAS observations. ISPRS Journal of Photogrammetry and Remote Sensing, 2017; 123: 20–34.
Huete A, Didan K, Miura T, Rodriguez E P, Gao X, Ferreira L G. Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sensing of Environment, 2002; 83: 195–213.
Gao B. NDWI - A normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sensing of Environment, 1996; 58: 257–266.
Ghimire B, Rogan J, Miller J. Contextual land-cover classification: incorporating spatial dependence in land-cover classification models using random forests and the Getis statistic. Remote Sensing Letters, 2010; 1(1): 45–54.
Pal M, Mather P M. An assessment of the effectiveness of decision tree methods for land cover classification. Remote Sensing of Environment, 2003; 86(4): 554–565.
Eisavi V, Homayouni S, Yazdi A M, Alimohammadi A. Land cover mapping based on random forest classification of multitemporal spectral and thermal images. Environmental Monitoring and Assessment, 2015; 187(5): 291.
Tian S H, Zhang X F, Tian J, Sun Q. Random forest classification of wetland landcovers from multi-sensor data in the arid region of Xinjiang, China. Remote Sensing, 2016; 8(11): 954.
Liaw A, Wiener M. Classification and regression by randomForest. R News, 2002; 2: 18–22.
Geiß C, Aravena Pelizari, P, Blickensdörfer L, Taubenbock H. Virtual Support Vector Machines with self-learning strategy for classification of multispectral remote sensing imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 2019; 151: 42–58.
Zendehboudi A, Baseer M A, Saidur R. Application of support vector machine models for forecasting solar and wind energy resources: A review. Journal of Cleaner Production, 2018; 199: 272–285.
Dou J, Yunus A P, Fbui D T, Merghadi A, et al. Assessment of advanced random forest and decision tree algorithms for modeling rainfall-induced landslide susceptibility in the Izu-Oshima Volcanic Island, Japan. Science of The Total Environment, 2019; 662: 332–346.
Bui D T, Pradhan B, Lofman O, Revhaug I. Landslide susceptibility assessment in Vietnam using support vector machines, decision tree, and Naive Bayes Models. Mathematical Problems in Engineering, 2012; 2012: 974638.
Ara Rahman S, Chakrabarty D. Sediment transport modelling in an alluvial river with artificial neural network. Journal of Hydrology, 2020; 588(5): 125056.
Dong Y H, Fu Z T, Peng Y Q, Zheng Y J, Yan H J, Li X X, et al. Precision fertilization method of field crops based on the Wavelet-BP neural network in China. Journal of Cleaner Production, 2020; 246: 118735.
Hemeida A M, Hassan S A, Mohamed A A, Alkhalaf S, Mahmoud M M, Senjyu T, et al. Nature-inspired algorithms for feed-forward neural network classifiers: a survey of one decade of research. Ain Shams Engineering Journal, 2020; 11(3): 659–675.
Wang L, Wang P X, Liang S L, Qi X, Li L, Xu L X. Monitoring maize growth conditions by training a BP neural network with remotely sensed vegetation temperature condition index and leaf area index. Computers and Electronics in Agriculture, 2019; 160: 82–90.
Han X, Wei Z, Zhang B Z, Li Y N, Du T S, Chen H. Crop evapotranspiration prediction by considering dynamic change of crop coefficient and the precipitation effect in back-propagation neural network model. Journal of Hydrology, 2021; 596: 126104.
Zhang J Q, Tian H R, Wang P X, Tansey K, Zhang S Y, Li H M. Improving wheat yield estimates using data augmentation models and remotely sensed biophysical indices within deep neural networks in the Guanzhong Plain, PR China. Computers and Electronics in Agriculture, 2022; 192: 106616.
Dong J W, Xiao X M, Menarguez M A, Zhang G L, Qin Y W, Thau D, et al. Mapping paddy rice planting area in northeastern Asia with Landsat 8 images, phenology-based algorithm and Google Earth Engine. Remote Sensing of Environment, 2016; 185: 142–154.
Foody G M. Status of land cover classification accuracy assessment. Remote Sensing of Environment, 2002; 80(1): 185–201.
Congalton R G. A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing of Environment, 1991; 37(1): 35–46.
Tan J B, Zuo J Q, Xie X Y, Ding M Q, Xu Z K, Zhou F B. MLAs land cover mapping performance across varying geomorphology with Landsat OLI-8 and minimum human intervention. Ecological Informatics, 2021; 61: 101227.
Ngo K D, Lechner A M, Vu T T. Land cover mapping of the Mekong Delta to support natural resource management with multi-temporal Sentinel-1A synthetic aperture radar imagery. Remote Sensing Applications: Society and Environment, 2020; 17: 100272.
Prasad P, Loveson V J, Chandra P, Kotha M. Evaluation and comparison of the earth observing sensors in land cover/land use studies using machine learning algorithms. Ecological Informatics, 2022; 68: 101522.
Hermosilla T, Wulder M A, White J C, Coops N C. Land cover classification in an era of big and open data: optimizing localized implementation and training data selection to improve mapping outcomes. Remote Sensing of Environment, 2022; 268: 112780.
Zhao Y F, Zhu W W, Wei P P, Fang P, Zhang X W, Yan N N, et al. Classification of Zambian grasslands using random forest feature importance selection during the optimal phenological period. Ecological Indicators, 2022; 135: 108529.
Fang H L, Zhang Y H, Wei S S, Li W J, Ye Y C, Sun T, et al. Validation of global moderate resolution leaf area index (LAI) products over croplands in northeastern China. Remote Sensing of Environment, 2019; 233: 111377.
Liu T, Abd-Elrahman A, Morton J, Wihelm V L. Comparing fully convolutional networks, random forest, support vector machine, and patch-based deep convolutional neural networks for object-based wetland mapping using images from small unmanned aircraft system. GIScience and Remote Sensing, 2018; 55(2): 243–264.
Liu W S, Yang J, Li P X, Han Y, Zhao J Q, Shi H T. A novel object-based supervised classification method with active learning and random forest for PolSAR imagery. Remote Sensing, 2018; 10(7): 1092.
Roth K L, Roberts D A, Dennison P E, Peterson S H, Alonzo. The impact of spatial resolution on the classification of plant species and functional types within imaging spectrometer data. Remote Sensing of Environment, 2015; 171: 45–57.
Lesiv M, Fritz S, McCallum I, Tsendbazar N, Herold M, Pekel J-F, et al. Evaluation of ESA CCI prototype land cover map at 20m. IIASA Working Paper, Laxenurg: IIASA, 2017; WP-17-021. Available: http://pure.iiasa.ac.at/14979/. Accessed on [2024-02-24].
Wang C S, Shu Q Q, Wang X Y, Guo B, Liu P, Li Q Q. A random forest classifier based on pixel comparison features for urban LiDAR data. ISPRS Journal of Photogrammetry and Remote Sensing, 2019; 148: 75–86.
Xie Z L, Chen Y L, Lu D S, Li G Y, hen E X. Classification of land cover, forest, and tree species classes with ZiYuan-3 multispectral and stereo data. Remote Sensing, 2019; 11(2): 164.
Xia J Y, Wan S Q. Independent effects of warming and nitrogen addition on plant phenology in the Inner Mongolian steppe. Annals of Botany, 2013; 111(6): 1207–1217.
Copyright (c) 2022 International Journal of Agricultural and Biological Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.