Comparison of Different Supervised Classification Algorithms for Mapping Paddy Rice Areas Using Landsat 9 Imageries

Year 2023, , 52 - 59, 27.09.2023

Melis İnalpulat

https://doi.org/10.46810/tdfd.1266393

Abstract

Rice is known to be one of the most essential crops in Turkey, as well as many other countries especially in Asia, whereas paddy rice cropping systems have a key role in many processes ranging from human nutrition to environment-related perspectives. Therefore, determination of cultivation area is still a hot topic among researchers from various disciplines, planners, and decision makers. In present study, it was aimed to evaluate performances of three classifications algorithms among most widely used ones, namely, maximum likelihood (ML), random forest (RF), and k-nearest neighborhood (KNN), for paddy rice mapping in a mixed cultivation area located in Biga District of Çanakkale Province, Turkey. Visual, near-infrared and shortwave infrared bands of Landsat 9 acquired in dry season of 2022 year was utilized. The classification scheme included six classes as dense vegetation (D), sparse vegetation (S), agricultural field (A), water surface (W), residential area – base soil (RB), and paddy rice (PR). The performances were tested using the same training samples and accuracy control points. The reliability of each classification was evaluated through accuracy assessments considering 150 equalized randomized control points. Accordingly, RF algorithym could identify PR areas with over 96.0% accuracy, and it was followed by KNN with 92.0%.

Keywords

Çanakkale, Landsat 9, Paddy rice, Performance comparison, Supervised classification algorithms

References

• [1] Song Y, Wang Y, Mao W, Sui H, Yong L, Yang D, et al. Dietary cadmium exposure assessment among the Chinese population. PLoS ONE 2017;12:e0177978.
• [2] Halder D, Saha JK, Biswas A. Accumulation of essential and non-essential trace elements in rice grain: Possible health impacts on rice consumers in West Bengal, India. Science of the Total Environment 2020;706:135944.
• [3] Wei J, Cui Y, Luo W, Luo Y. Mapping paddy rice distribution and cropping intensity in China from 2014 to 2019 with Landsat images, effective flood signals, and Google Earth Engine. Remote Sensing, 2022;14:759.
• [4] Muthayya JD, Sugimoto SD, Montgomery S, Maberly GF. An overview of global rice production, supply, trade, and consumption. Annals of the New York Academy of Sciences 2014;1324(1):7-14.
• [5] Xia L, Zhao F, Chen J, Yu L, Lu M, Yu Q, et al. A full resolution deep learning network for paddy rice mapping using Landsat data. ISPRS Journal of Photogrammetry and Remote Sensing 2022;194:91-107.
• [6] Saltık B, Genc L. Rice area determination using Landsat-based indices and land surface temperature values. International Journal of Agricultural and Biosystems Engineering 2016;10(7):462-470.
• [7] Semerci A., Everest B. Econometric analysis of paddy production in Çanakkale Province. Türk Tarım ve Doğa Bilimleri Dergisi 2021;8(3):576-584.
• [8] Cao J, Cai X, Tan J, Cui Y, Xie H, Liu F, et al. Mapping paddy rice using Landsat time series data in the Ganfu Plain irrigation system, Southern China, from 1988-2017. International Journal of Remote Sensing 2021;42(4):1556-1576.
• [9] Smartt AD, Brye KR, Rogers CW, Norman RJ, Gbur EE, Hardke JT, et al. Previous crop and cultivar effects on methane emissions from drill-seeded, delayed-flood rice grown on a clay soil. Applied and Environmental Soil Science 2016:9542361.
• [10] Dong J, Xiao X, Menarguez MA, Zhang G, Qin Y, 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.
• [11] Nguyen DB, Wagner W. European rice cropland mapping with Sentinel-1 data: the Mediterranean region case study. Water 2017;9:372.
• [12] McCloy KR, Smith FR, Robinson MR. Monitoring rice areas using Landsat MSS data. International Journal of Remote Sensing 1987;8:741-749.
• [13] Thorp KR, Drajat D. Deep machine learning with Sentinel satellite data to map paddy rice production stages across West Java, Indonesia. Remote Sensing of Environment 2021;265:112679.
• [14] Basheer S, Wang X, Farooque AA, Nawaz RA, Liu K, Adekanmbi T, et al. Comparison of land use land cover classifiers using different satellite imagery and machine learning techniques. Remote Sensing 2022;14:4978.
• [15] Mishra VN, Prasad R, Kumar P, Srivastava PK, Rai PK. Knowledge-based decision tree approach for mapping spatial distribution of rice crop using C-band synthetic aperture radar-derived information. Journal of Applied Remote Sensing 2017;11:046003.
• [16] Onojeghuo AO, Blackburn GA, Wang QM, Atkinson PM, Kindred D, Miao XY. Mapping paddy rice fields by applying machine learning algorithms to multi-temporal Sentinel-1A and Landsat data. International Journal of Remote Sensing 2018;39:1042-1067.
• [17] Karkee M, Steward BL, Tang L, Aziz SA. Quantifying sub-pixel signature of paddy rice field using an artificial neural network. Computers and Electronics in Agriculture 2009;65:65-76.
• [18] Turkish Statistical Institute [Internet] 2022 [Cited 2023 January 24]. Available from: https://biruni.tuik.gov.tr/medas/?locale=tr
• [19] United States Geological Survey [Internet] 2022 [Cited 2022 December 16]. Available from: https://earthexplorer.usgs.gov
• [20] Richards JA, Jia X. Remote sensing digital image analysis: An introduction. Berlin: Springer Verlag; 2006.
• [21] Breiman, L. Random forests. Machine Learning, 2001;45(1):5-32.
• [22] Fix E, Hodges JL. Discriminatory Analysis, Nonparametric Discrimination: Consistency Properties; Technique Report No. 4; U.S. Air Force School of Aviation Medicine, Randolf Field Texas: Universal City, TX, USA; 1951. p. 238-247.
• [23] Erdanaev E, Kappas M, Wyss D. The identification of irrigated crop types using support vector machine, random forest and maximum likelihood classification methods with Sentinel-2 data in 2018: Tashkent Province, Uzbekistan. International Journal of Geoinformatics, 2022;18(2):37-53.
• [24] Berhane TM, Lane CR, Wu Q, Autrey BC, Anenkhonov OA, Chepinoga VV, et al. Decision-tree, rule-based, and random forest classification of high-resolution multispectral imagery for wetland mapping and inventory. Remote sensing 2018;10(4):580.
• [25] Kalpana YB, Nandhagopal SM. LULC image classifications using k-means clustering and knn algorithm. Dynamic Systems and Applications 2021;30(10):1640-1652.
• [26] Hedayati A, Mohammad HV, Behzadi S. Paddy lands detection using Landsat-8 satellite images and object-based classification in Rasht city, Iran. The Egyptian Journal of Remote Sensing and Space Science 2022;25(1):73-84.
• [27] Gomez C, White JC, Wulder AA. Optical remotely sensed time series data for land cover classification: A review. ISPRS Journal of Photogrammetry and Remote Sensing 2016;116:55-72.
• [28] Yuh YG, Tracz W, Matthews HD, Turner SE. (Application of machine learning approaches for land cover monitoring in northern Cameroon. Ecological Informatics, 2023;74:101955.
• [29] Johnson B. Scale issues related to the accuracy assessment of land use/land cover maps produced using multi-resolution data: Comments on “The improvement of land cover classification by thermal remote sensing”. Remote Sensing 2015, 7, 8368-8390. Remote Sensing 2015;7:13436-13439.
• [30] Zhao Y, Gong P, Yu L, Hu L, Li X, Li C, et al. Towards a common validation sample set for global land-cover mapping. International Journal of Remote Sensing, 2014;35:4795-4814.
• [31] Abdi-Sukmono A. Identification of rice field using multi-temporal NDVI and PCA method on Landsat 8 (Case Study: Demak, Central Java). IOP Conf. Ser.:Earth and Environmental Science 2017;54:012001.
• [32] Zhao R, Li Y, Ma M. Mapping Paddy Rice with Satellite Remote Sensing: A Review. Sustainability 2021;13:503.
• [33] Zhang M, Lin H, Wang G, Sun H, Fu J. Mapping paddy rice using a convolutional neural network (CNN) with Landsat 8 datasets in the Dongting Lake Area, China. International Remote Sensing, 2018;10:1840.
• [34] Phan TN, Kuch V, Lehnert LW. Land cover classification using Google Earth Engine and random forest classifier - the role of image composition. Remote Sensing 2020;12:2411.
• [35] Mahdianpari M, Salehi B, Mohammadimanesh F, Motagh M. Random forest wetland classification using ALOS-2 L-band, RADARSAT-2 C-band and TerraSAR-X imagery. ISPRS Journal of Photogrammetry and Remote Sensing 2017;130:13-31.
• [36] Xia J, Falco N, Benediktsson JA, Du P, Chanussot J. Hyperspectral image classification with rotation random forest via KPCA. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2017;10(4): 1601-1609.
• [37] Rodriguez-Galiano VF, Chica-Rivas M. Evaluation of different machine learning methods for land cover mapping of a Mediterranean area using multi-seasonal Landsat images and Digital Terrain Models. International Journal of Digital Earth 2012;7:492-509.
• [38] Abdel-Rahman EM, Mutanga O, Adam E, Ismail R. Detecting Sirex noctilio grey-attacked and lightning-struck pine trees using airborne hyperspectral data, random forest and support vector machines classifiers. ISPRS Journal of Photogrammetry and Remote Sensing 2014;88:48-59.
• [39] Van-Beijma S, Comber A, Lamb A. Random forest classification of salt marsh vegetation habitats using quad-polarimetric airborne SAR, elevation and optical RS data. Remote Sensing of the Environment 2014;149:118-129.
• [40] Zhu A-X, Zhau F-X, Pan H-B, Liu J-Z. Mapping rice paddy distribution using remote sensing by coupling deep learning with phenological characteristics. Remote Sensing 2021;13(7):1360.
• [41] Yao J, Wu J, Xiao J, Zhang Z, Li J. The Classification Method Study of Crops Remote Sensing with Deep Learning, Machine Learning, and Google Earth Engine. Remote Sensing, 2022;14:2758.