[1]柳涛,盖艾鸿*,赵鹏伟,等.基于Sentinel-2影像的果树提取方法及其空间分析研究——以甘肃省平凉市为例[J].江苏林业科技,2024,51(03):22-29.[doi:10.3969/j.issn.1001-7380.2024.03.005]
　Liu Tao,Gai Aihong*,Zhao Pengwei,et al.Apple tree extraction and spatial analysis based on Sentinel-2 Image——A case study of Pingliang, Gansu Province[J].Journal of Jiangsu Forestry Science &Technology,2024,51(03):22-29.[doi:10.3969/j.issn.1001-7380.2024.03.005]
点击复制

基于Sentinel-2影像的果树提取方法及其空间分析研究——以甘肃省平凉市为例()
分享到：

《江苏林业科技》[ISSN:1001-7380/CN:32-1236/S]

卷:
第51卷
期数:
2024年03期
页码:
22-29
栏目:
试验研究
出版日期:
2024-06-30

文章信息/Info

Title:
Apple tree extraction and spatial analysis based on Sentinel-2 Image——A case study of Pingliang, Gansu Province
文章编号:
1001-7380（2024）03-0022-08
作者:
柳涛; 盖艾鸿*; 赵鹏伟; 刘桦; 鲁聪聪; 李莺莺
甘肃农业大学资源与环境学院,甘肃 兰州 730070
Author(s):
Liu Tao;  Gai Aihong*;  Zhao Pengwei;  Liu Hua;  Lu Congcong;  Li Yingying
College of Resources and Environment, Gansu Agricultural University, Lanzhou 730070,China
关键词:
遥感; 梯度提升树' target="_blank" rel="external">">; 数据增强; Sentinel-2影像; Kappa系数; 平凉市
Keywords:
Remote sensing;  Gradient boosting tree;  Data augmentation;  Sentinel-2 remote sensing image;  Kappa coefficience;  Pingliang City
分类号:
S661.1；TP753；TP79
DOI:
10.3969/j.issn.1001-7380.2024.03.005
文献标志码:
A
摘要:
利用遥感技术对果园进行快速监测，准确掌握苹果园地面积与空间种植分布状况，有助于促进当地经济的发展。目前针对丘陵区果园提取的研究较少，相关方法的有效性和可靠性仍然存在问题。以甘肃省平凉市为研究区域，采用NDVI,RVI,EVI,SIPI,LSWI,NDWI等指标对输入数据进行增强，通过基于数据增强的梯度提升树算法提取研究区苹果种植面积。为验证该方法的有效性，引入最小距离法、CART决策树法、支持向量机法和随机森林4种机器学习算法进行对比分析，结果表明，梯度提升树算法分类精度最高，总体分类精度（Overall Accuracy, OA）达到89.3%，Kappa系数为0.77，分类效果及一致性均最佳。此外，采用基于数据增强的梯度提升树法分别对2019—2023年的苹果园进行提取，获得平凉市苹果园种植变化情况，各区县苹果园种植面积除泾川县外整体呈现上升趋势，泾川县和静宁县种植面积最大，其次为庄浪县、灵台县和崆峒区，最小的为崇信县和华亭市。
Abstract:
Using remote sensing technology to quickly monitor orchards and accurately grasp the area and spatial distribution of apple orchards can help promote local economic development. At present, there is relatively little research on the extraction of orchards in hilly areas, and the effectiveness and reliability of related methods were still controversial. Taking Pingliang City, Gansu Province as the research area, such indicators as NDVI, RVI, EVI, SIPI, LSWI, and NDWI were used to enhance the input data. The gradient boosting tree algorithm based on data augmentation was used to extract the orchard planting area in the research area. To verify the effectiveness of the method proposed in this article, four machine learning algorithms, namely the minimum distance method, CART decision tree method, support vector machine method, and random forest method, were introduced for comparative analysis. The classification results showed that the gradient boosting tree algorithm had the highest classification accuracy, with an overall classification accuracy (OA) of 89.3% and a Kappa coefficient of 0.77. The classification performance and consistency were the best. In addition, the gradient boosting tree method based on data augmentation was used to extract the changes in orchard planting in Pingliang City from 2019 to 2023. The planting area of orchards in each district and county shows an overall upward trend, except for Jingchuan County. Jingchuan County and Jingning County have the largest planting area, followed by Zhuanglang County, Lingtai County, and Kongtong District, and the smallest are Chongxin County and Huating City.

参考文献/References:

[1]方福平,程式华.水稻科技与产业发展[J].农学学报,2018,8(1):92-98.
[2]陆娣,付雪娇,岳铭鉴.辽宁省水稻产业发展现状及政策建议[J].辽宁农业科学,2020(6):57-59.
[3]杜培军,夏俊士,薛朝辉,等.高光谱遥感影像分类研究进展[J].遥感学报,2016,20(2):236-256.
[4]杨庆振,郭敏,范新成.基于随机森林算法的高光谱遥感作物分类[J].测绘与空间地理信息,2023,46(4): 149-151,154.
[5]马玥,姜琦刚,孟治国,等.基于随机森林算法的农耕区土地利用分类研究 [J].农业机械学报,2016,47 (1): 297-303.
[6]王全才.随机森林特征选择[D].大连:大连理工大学,2011.
[7]李宏达.基于梯度提升树和随机森林的Sentinel-2多季相数据土地覆被分类研究[D].西宁:青海师范大学, 2021.
[8]FRIEDMAN J H.Stochastic gradient boosting[J]. Computational Statistics & Data Analysis,2002,38(4): 367-378.
[9]李根.基于梯度提升决策树的高速公路交织区汇入模型 [J].东南大学学报(自然科学版),2018,48(3): 563-567.
[10]PRODHAN F A, ZHANG J, HASAN S S, et al. A review of machine learning methods for drought hazard monitoring and forecasting: Current research trends, challenges, and future research directions[J].Environmental Modelling & Software,2022,149:105327.
[11]马陇飞,萧汉敏,陶敬伟,等.基于梯度提升决策树算法的岩性智能分类方法[J].油气地质与采收率,2022, 29 (1): 21-29.
[12]秦泉,王冰,李峰,等.面向对象的GF-1卫星影像苹果树种植面积遥感提取研究——以山地丘陵地区的栖霞市为例[J].沙漠与绿洲气象,2020,14(2):129-136.
[13]周欣兴,赵林,张文杰,等.基于Sentinel-2多时相影像的果树种植区遥感提取[J].浙江农业学报,2022,34 (12): 2767-2777.
[14]WARNER T A,SHANK M C.Spatial autocorrelation analysis of hyperspectral imagery for feature selection[J]. Remote Sensing of Environment,1997,60(1):58-70.
[15]LUCAS R,BUNTING P,PATERSON M, et al. Classification of Australian forest communities using aerial photography, CASI and HyMap data[J]. Remote Sensing of Environment,2008,112(5):2088-2103.
[16]SAOUR H.An NDVI synthesis method for multi-temporal remote sensing images based on k-NN learning: a case based on Landsat 8 data[J].Remote Sensing Letters, 2018,9:6.
[17]张凌凡,陈忠辉,周天白,等.基于梯度提升决策树的露天矿边坡多源信息融合与稳定性预测[J].煤炭学报, 2020, 45 (S1): 173-180.
[18]LAWRENCE R, BUNN A, POWELL S, et al. Classification of remotely sensed imagery using stochastic gradient boosting as a refinement of classification tree analysis[J]. Remote Sensing of Environment,2004, 90(3): 331-336.
[19]FRIEDMAN J H. Greedy function approximation: a gradient boosting machine[J].Annals of Statistics, 2001: 1189-1232.
[20]芦倩,赵维俊,黄鑫.基于高分辨率遥感影像的土壤类型制图研究[J].甘肃农业大学学报,2022,57(6):188-197.
[21]MARTIN M E, NEWMAN S D, ABER J D, et al. Determining forest species composition using high spectral resolution remote sensing data[J]. Remote Sensing of Environment, 1998, 65(3): 249-254.
[22]吴路华,陈丹,杨东妮.贵州武陵山区植被NDVI时空演变及其未来持续性特征[J].科学技术创新,2023(23):75-79.
[23]GRAJSKI K A, BREIMAN L, DI PRISCO G V, et al. Classification of EEG spatial patterns with a tree-structured methodology: CART[J]. IEEE Transactions on Biomedical Engineering, 1986 (12): 1076-1086.
[24]LIU W, CHEN Z, HU Y, et al. A systematic machine learning method for reservoir identification and production prediction[J]. Petroleum Science, 2023, 20(1): 295-308.
[25]许文宁,王鹏新,韩萍,等.Kappa系数在干旱预测模型精度评价中的应用——以关中平原的干旱预测为例[J].自然灾害学报,2011,20(6): 81-86.
[26]李慧.一种改进的随机森林并行分类方法在运营商大数据的应用[D].成都:电子科技大学,2015.
[27]罗信,闫奇奇,宋思涵,等.遥感影像中辫状河道提取的CART决策树分类方法研究[J].计算机时代,2022(8):6-9.
[28]党 涛,李亚妮,罗军凯,等.基于最小距离法的面向对象遥感影像分类[J].测绘与空间地理信息,2017,40(10):163-165,169,173.
[29]李一蜚,秦凯,李丁,等.基于梯度提升回归树算法的地面臭氧浓度估算[J].中国环境科学,2020,40(3): 997-1007.
[30]NIU W, LU J, SUN Y. Development of shale gas production prediction models based on machine learning using early data[J]. Energy Reports,2022,8:1229-1237.
[31]李根.基于梯度提升决策树的高速公路交织区汇入模型[J].东南大学学报(自然科学版),2018,48(3): 563-567.
[32]张凌凡,陈忠辉,周天白,等.基于梯度提升决策树的露天矿边坡多源信息融合与稳定性预测[J].煤炭学报, 2020, 45 (S1): 173-180.
[33]VAPNIK V, CHAPELLE O.Bounds on error expectation for support vector machines[J].Neural Computation, 2000,12(9): 2013-2036.
[34]方匡南,吴见彬,朱建平,等.随机森林方法研究综述[J].统计与信息论坛,2011,26(3):32-38.

相似文献/References:

[1]崔立,闫保银.基于遥感技术的森林蓄积量估测研究进展[J].江苏林业科技,2020,47(04):45.[doi:10.3969/j.issn.1001-7380.2020.04.011]
[2]林春穆.基于多光谱数据初探野生长叶榧分布光谱特征[J].江苏林业科技,2022,49(01):28.[doi:10.3969/j.issn.1001-7380.2022.01.005]
　Lin Chunmu.Identification of distribution of wild Torreya jackii Chun in Jiangshi Nature Reserve based on spectral characteristics[J].Journal of Jiangsu Forestry Science &Technology,2022,49(03):28.[doi:10.3969/j.issn.1001-7380.2022.01.005]
[3]刘云鹏,解春霞,李莉,等.无人机遥感监测技术在松材线虫病疫情监测中的应用探讨[J].江苏林业科技,2022,49(02):52.[doi:10.3969/j.issn.1001-7380.2022.02.010]
　Liu Yunpeng,Xie Chunxia,Li Li,et al.Discussion on the application of UAV remote sensing technology in monitoring of PWD[J].Journal of Jiangsu Forestry Science &Technology,2022,49(03):52.[doi:10.3969/j.issn.1001-7380.2022.02.010]

备注/Memo

备注/Memo:
收稿日期：2024-01-11;修回日期：2024-03-21
基金项目：甘肃农业大学科技创新基金农业资源与环境一级学科开放基金(GAU-XKJS-2018-216);国家自然科学基金“融合星地多源数据的作物干旱过程定量监测方法研究”(42075120)
作者简介：柳涛（1999- ），男，甘肃张掖人，硕士研究生。主要从事 GIS在农业资源利用领域中的研究。E-mail:t18189614040@163.com
*通信作者：盖艾鸿(1967- )，男，甘肃平凉人，教授，博士。主要从事农业资源信息管理方面的研究。
更新日期/Last Update: 2024-07-30