基于神经网络模型的干旱区绿洲土壤盐渍化评价分析

doi:10.3724/SP.J.1047.2017.00983

地球信息科学学报 ›› 2017, Vol. 19 ›› Issue (7): 983-993.doi: 10.3724/SP.J.1047.2017.00983

基于神经网络模型的干旱区绿洲土壤盐渍化评价分析

姜红¹(), 玉素甫江·如素力^1,^2,^*(), 热伊莱·卡得尔¹, 阿迪来·乌甫¹

1. 新疆师范大学地理科学与旅游学院流域信息集成与生态安全实验室,乌鲁木齐 830054
2. 新疆干旱区湖泊环境与资源重点实验室,乌鲁木齐 830054

收稿日期:2017-01-03 修回日期:2017-02-23 出版日期:2017-07-10 发布日期:2017-07-10
作者简介:
作者简介：姜红（1991-）,男,重庆人,硕士生,主要从事资源环境遥感研究。E-mail:xjnujh@163.com
基金资助:
新疆师范大学地理学博士点支撑学科开放课题基金项目(XJNU-DL-201605);国家自然科学基金项目(41161007、41661047);新疆维吾尔族自治区青年科技创新人才培养工程项目(QN2015YX009)

Evaluation and Analysis of Soil Salinization in the Arid Zones based on Neural Network Model

JIANG Hong¹(), YUSUFUJIANG Rusuli^1,^2,^*(), REYILAI Kadeer¹, ADILAI Wufu¹

1. Institute of Geographical Science and Tourism / Laboratory of Information Integration and Eco-Security, Xinjiang Normal University, Urumqi 830054, China
2. Xinjiang Key Laboratory of lake Environment and Resources in Arid Zone, Urumqi 830054, China

Received:2017-01-03 Revised:2017-02-23 Online:2017-07-10 Published:2017-07-10
Contact: YUSUFUJIANG Rusuli

摘要/Abstract

摘要：

土壤盐渍化严重制约了农业可持续发展和生态安全,土壤盐渍化的精确评价分析,对土壤盐渍化的改善和治理具有重要的意义。本文以新疆焉耆盆地为研究对象,Landsat8 OLI遥感影像和实测采样数据相结合,提取地下水埋深（GD）、盐分指数（SI）、地表蒸散量（SET）和改进型温度植被干旱指数（MTVDI）建立了土壤盐渍化评价模型。结果表明：①结合野外实测土壤盐分数据,对BP神经网络模型进行训练。最终以最优的4-4-1结构的3层BP神经网模型对研究区土壤盐渍化进行了预测（R²=0.864,RMSE=0.569）。相比传统多元线性回归模型（R²=0.741,RMSE=0.767）,神经网络模型对土壤盐渍化的预测精度更高;②土壤盐渍化分布与GD、SI、SET和MTVDI等存在较强的关联性,不同等级的土壤盐渍化是不同影响因素不同程度上组合而引起的结果,盐渍化土地主要分布在地下水位较低以及土地开垦之后没有利用的荒地区域;③整个研究区大部分区域受到不同程度的盐渍化影响,耕地退化为盐渍地导致该区域土壤盐渍化以及土壤次生盐渍化进一步加剧。

关键词: 盐渍化, 神经网络, 遥感, 预测, 焉耆盆地

Abstract:

Soil salinization is the process of increasing the salt content in the soil. Salinization occurs when the groundwater table is between two and three meters from the surface of the soil in arid lands. The salts from the groundwater are raised by capillary action to the surface of the soil, and it affects human and natural resources, such as native vegetation and crops, animals, infrastructure, agricultural inputs, biodiversity, aquatic ecosystems and water supply quality in the environment. Factors such as climate, features of landscape, soils, drainage, aspect and the effects of human activities all impact on the severity and occurrence of salinization. Therefore, it is an important concern to evaluate and monitor soil salinity in order to take protective measures against further deterioration of the soil. Traditionally, soil salinity evaluation and monitoring are often carried out with intensive field work and sampling. Most previous studies have focused on differentiating salinized and non-salinized soil qualitatively by analyzing the salinity distribution and monitoring its dynamics. Remote Sensing (RS), Geographical Information Systems (GIS) and modeling have recently outperformed the traditional methods. Remotely sensed data has great potential for monitoring dynamic processes, including salinization. Remote sensing of surface features using aerial photography, videography, infrared thermometry, and multispectral scanners has been used intensively to identify and map salt-affected areas. Salinization has seriously restricted the sustainable development of agriculture and ecological security in the Yanqi Basin, Xinjiang, China. Therefore, accurate assessment and monitoring of soil salinization is particularly important. In this paper, based on the Landsat 8 OLI remote sensing data and measured data, the soil salinization evaluation model was established by using the four evaluation indexes of groundwater depth (GD), salinity index (SI), surface evapotranspiration (SET) and modified temperature vegetation dryness index (MTVDI) in Yanqi basin, Xinjiang. Results demonstrate that: (1) BP neural network model for training was combined with the field measured soil salinity data and the best performance was archived in 4-4-1 architecture (R²=0.864, RMSE=0.569) in the three networks. Compared with traditional multiple linear regression model (R²=0.741, RMSE=0.767), the artificial neural network can improve the predictive accuracy of soil salinization. (2) Soli salinization is strongly associated with GD、SI、SET and MTVDI, and the soil salinization are the results of different combinations of different combination effect factors. Salinization is mainly distributed in low groundwater level and unused area. (3) Most of the study area was salinized in different degrees of salinization, and the degradation of farmland led to further soil salinization and secondary soil salinization.

Key words: salinization, neural network, remote sensing, forecasting, Yanqi Basin

姜红, 玉素甫江·如素力, 热伊莱·卡得尔, 阿迪来·乌甫. 基于神经网络模型的干旱区绿洲土壤盐渍化评价分析[J]. 地球信息科学学报, 2017, 19(7): 983-993.DOI:10.3724/SP.J.1047.2017.00983

JIANG Hong,YUSUFUJIANG Rusuli,REYILAI Kadeer,ADILAI Wufu. Evaluation and Analysis of Soil Salinization in the Arid Zones based on Neural Network Model[J]. Journal of Geo-information Science, 2017, 19(7): 983-993.DOI:10.3724/SP.J.1047.2017.00983

图/表 15

图1

图2

图3

图4

图5

图6

图7

图8

表1

表2

图9

图10

图11

图12

表3

参考文献 27

[1]	孙倩,塔西甫拉提·特依拜,丁建丽,等.干旱区典型绿洲土地利用/覆被变化及其对土壤盐渍化的效应研究——以新疆沙雅县为例[J].地理科学进展,2012,31(9):1212-1223. doi: 10.11820/dlkxjz.2012.09.013
	[ Sun Q, Tashpolat·Tiyip, Ding J L, et al. Study on land use/cover changes and soil salinization in dry areas: a case study of Shaya county in Xinjiang[J]. Progress in Geography, 2012,31(9):1212-1223. ] doi: 10.11820/dlkxjz.2012.09.013
[2]	翁永玲,宫鹏.土壤盐渍化遥感应用研究进展[J].地理科学,2006,26(3):369-375.
	[ Weng Y L, Gong P.A review on remote sensing technique for salt-affected soils[J]. Scientia Geographica Sinica, 2006,26(3):369-375. ]
[3]	王遵亲,祝寿泉,俞仁培,等.中国盐渍土[M].北京:科学出版社,1993:7-78.
	[ Wang Z Q, Zhu S Q, Yu R P, et al.Chinese Saline soil[M]. Beijing: Science Press, 1993:7-78. ]
[4]	张荣群,乔月霞,薛佳妮.银川平原土壤盐渍化与土地利用强度的空间关联分析[J].地球信息科学学报,2015,17(5):598-606. doi: 10.3724/SP.J.1047.2015.00598
	[ Zhang R Q, Qiao Y X, Xue J N.Spatial relationship analysis between the soil salinization and land use intensity in Yinchuan Plain[J]. Journal of Geo-information Science, 2015,17(5):598-606. ] doi: 10.3724/SP.J.1047.2015.00598
[5]	丁建丽,陈文倩,陈芸.干旱区土壤盐渍化灾害预警——以渭——库绿洲为例[J].中国沙漠,2016,36(4):1079-1086. doi: 10.7522/j.issn.1000-694X.2015.00067
	[ Ding J L, Chen W Q, Chen Y.Soil salinization disaster warning in arid zones: A case study in the Ugan-Kuqa oasis[J]. Journal of Desert Research, 2016,36(4):1079-1086. ] doi: 10.7522/j.issn.1000-694X.2015.00067
[6]	王静,刘湘南,黄方,等.基于ANN技术和高光谱遥感的盐渍土盐分预测[J].农业工程学报,2009,25(12):161-166. doi: 10.3969/j.issn.1002-6819.2009.12.029
	[ Wang J, Liu X N, Huang F, et al. Salinity forecasting saline soil based on ANN and hyperspectral remote sensing[J].Transactions of the CSAE, 2009,25(12):161-166. ] doi: 10.3969/j.issn.1002-6819.2009.12.029
[7]	史晓霞,王静,任春颖,等.基于GIS与Geo-CA模型的半干旱区土壤盐碱化动态模拟研究[J].东北师范大学学报(自然科学版),2004,36(2):88-94. doi: 10.3321/j.issn:1000-1832.2004.02.016
	[ Shi X X, Wang J, Ren C Y, et al.Study on the modeling of soil salinization in semi-arid area based on GIS and Geo-CA model[J]. Journal of Northeast Normal University, 2004,36(2):88-94. ] doi: 10.3321/j.issn:1000-1832.2004.02.016
[8]	陈实,高超,徐斌,等.新疆石河子农区土壤含盐量定量反演及其空间格局分析[J].地理研究,2014,33(11):2135-2144. doi: 10.11821/dlyj201411013
	[ Chen S, Gao C, Xu B, et al.Quantitative inversion of soil salinity and analysis of its spatial pattern in agricultural area in Shihezi of Xinjiang[J]. Geographical Research, 2014,33(11):2135-2144. ] doi: 10.11821/dlyj201411013
[9]	谢姆斯叶·艾尼瓦尔,塔西甫拉提·特依拜,王宏卫,等.人工智能计算技术在新疆干旱区典型绿洲土壤盐分预测中的应用[J].中国沙漠,2014,34(1):153-161. doi: 10.7522/j.issn.1000-694X.2013.00294
	[ Shamsiya·Anwar, Tashpolat·Tiyip, Wang H W, et al. Application of artificial intelligent technique for predicting soil salinity in a Typical oasis of arid area in Xinjiang, China[J]. Journal of Desert Research, 2014,34(1):153-161. ] doi: 10.7522/j.issn.1000-694X.2013.00294
[10]	买买提·沙吾提,塔西甫拉提·特依拜,丁建丽,等.基于GIS的干旱区土壤盐渍化敏感性评价——以渭干河—库车河三角洲绿洲为例[J].资源科学,2012,34(2):353-358.
	[ Mamatsawut, Tashpolat·Tiyip, Ding J L, et al. A GIS-based assessment on sensitivity of soil salinization in arid areas: a case study of the Ugan-Kuqa river delta[J]. Resources Science, 2012,34(2):353-358. ]
[11]	玉素甫江·如素力.新疆焉耆盆地二元水循环过程模拟研究[D].北京:中国科学院大学,2015:27-28.
	[ Yusufujiang R.Research on dual water cycling simulation in Yanqi Basin,Xinjiang[D].Beijing: University of Chinese Academy of Sciences, 2015:27-28. ]
[12]	蔡阿兴,陈章英,蒋正琦,等.我国不同盐渍地区盐分含量与电导率的关系[J].土壤,1997,29(1):54-57.
	[ Cai A X, Chen Z Y, Jiang Z Q, et al.Relationship between salt content and conductivity in different saline areas in China[J].Soils, 1997,29(1):54-57. ]
[13]	韩桂红,塔西甫拉提·特依拜,买买提·沙吾提,等.渭-库绿洲地下水对土壤盐渍化和其逆向演替过程的影响[J].地理科学,2012,32(3):362-367.
	[ Han G H, Tashpolat·Tiyip, Mamatsawt, et al. Influence of groundwater on soil salinization and its reversal evolvement in Wei-ku oasis[J].Scientia Geographica Sinica, 2012,32(3):362-367. ]
[14]	王水献,周金龙,董新光.地下水浅埋区土壤水盐试验分析[J].新疆农业大学学报,2004,27(3):52-56.
	[ Wang S X, Zhou J L, Dong X G.Experimental analysis on the soil water and salt dynamic variation in shallow groundwater areas[J]. Journal of Xinjiang Agricultural University, 2004,27(3):52-56. ]
[15]	塔西甫拉提·特依拜,阿布都瓦斯提·吾拉木.绿洲——荒漠交错带地下水位分布的遥感模型研究[J].遥感学报,2002,6(4):299-306. doi: 10.3321/j.issn:1007-4619.2002.04.011
	[ Tashpolat·Tiyip, Abduwasit·Ghulam. Research on model of groundwater level distribution in the oasis and desert ecotone using remote sensing[J]. Journal of Remote Sensing, 2002,6(4):299-306. ] doi: 10.3321/j.issn:1007-4619.2002.04.011
[16]	哈学萍,丁建丽,塔西甫拉提·特依拜,等.基于SI-Albedo特征空间的干旱区盐渍化土壤信息提取研究——以克里雅河流域绿洲为例[J].土壤学报,2009,46(3):381-390. doi: 10.3321/j.issn:0564-3929.2009.03.002
	[ Ha X P, Ding J L, Tashpolat·Tiyip, et al. SI-albedo space-based extraction of salinization information in arid area[J]. Acta Pedologica Sinica, 2009,46(3):381-390. ] doi: 10.3321/j.issn:0564-3929.2009.03.002
[17]	郭亮,沈志,申旭辉,等.干旱区盐渍地土壤含水量分布及其光谱特征研究[J].安徽农业科学,2015,43(15):102-106.
	[ Guo L, Shen Z, Shen X H, et al.Study on soil moisture distribution and spectral characteristics of soil in arid region[J]. Journal of Anhui Agricature, 2015,43(15):102-106. ]
[18]	姜红,玉素甫江·如素力,热伊莱·卡得尔,等.不同空间插值方法对博斯腾湖水体矿化度的适应性评价研究[J].新疆师范大学学报(自然科学版),2016,35(4):7-14.
	[ Jiang H, Yusufujiang·Rusuli, Reyilai·Kadeer, et al. Study on suitability of different interpolation methods for evaluation of water salinity in Bosten Lake[J]. Journal of Xinjiang Normal University(Natural Sciences Edition), 2016,35(4):7-14. ]
[19]	Sandholt I, Rasmussen K, Andersen J.A simple interpretation of the surface temperature/vegetation index space for assessment of surface moisture status[J]. Remote Sensing of Environment, 2002,79(2):213-224. doi: 10.1016/S0034-4257(01)00274-7
[20]	陈艳华,张万昌.植被类型对温度植被干旱指数(TVDI)的影响研究——以黑河绿洲区为例[J].遥感技术与应用,2007,22(6):700-706. doi: 10.3969/j.issn.1004-0323.2007.06.006
	[ Chen Y H, Zhang W C.Evaluating effects of vegetationtypes on temperature vegetation drought index(TVDI) in the Heihe oasis region[J]. Remote Sensing Technology and Application, 2007,22(6):700-706. ] doi: 10.3969/j.issn.1004-0323.2007.06.006
[21]	Qi J, Chehbouni A, Huete A R, et al.A modified soil adjusted vegetation index[J]. Remote Sensing of Environment, 1994,48(2):119-126. doi: 10.1016/0034-4257(94)90134-1
[22]	文军,王介民.一种由卫星遥感资料获得的修正的土壤调整植被指数[J].气候与环境研究,1997,2(3):302-309.
	[ Wen J, Wang J M. A modified soil-adjusted vegetation index obtained from satellite remote sensing data[J]. Climatic and Environmental Ressarch, 1997,2(3):302-309. ]
[23]	覃志豪,Zhang M H, Amon K,等.用陆地卫星TM6数据演算地表温度的单窗算法[J].地理学报,2001,56(4):456-466.
	[ Qin Z H, Zhang M H, Amon K, et al.Mono-window algorithm for retrieving land surface temperature from landsat TM6 data[J]. Acta Geographica Sinica, 2001,56(4):456-466. ]
[24]	楼琇林,黄韦艮.基于人工神经网络的赤潮卫星遥感方法研究[J].遥感学报,2003,7(2):125-130. doi: 10.3321/j.issn:1007-4619.2003.02.008
	[ Lou X L, Huang W G.An artificial neural network method for detecting red tides with NOAA AVHRR imagery[J]. Journal of Remote Sensing, 2003,7(2):125-130. ] doi: 10.3321/j.issn:1007-4619.2003.02.008
[25]	Dreyer P.Classification of land cover using optimized neural nets on SPOT data[J]. Photogrammetric Engineering & Remote Sensing, 1993,59(5):617-621. doi: 10.1016/0031-0182(93)90010-G
[26]	Zhang Y Z, Pullianinen J, Koponen S, et al.Application of an empirical neural network to surface water quality estimation in the Gulf of Finland using combined optical data and microwave data[J]. Remote Sensing of Environment, 2002,81(2/3):327-336. doi: 10.1016/S0034-4257(02)00009-3
[27]	新疆农业厅,新疆普查办公室.新疆土壤[M].北京:科学出版社,1996:151-521.
	[ Xinjiang department of agricultural, Xinjiang soil survey office eds. The soil of Xinjiang. Beijing: Science Press, 1996:151-521. ]

MTVDI	SI	GD/m	SET/mm	MTVDI	SI	GD/m	SET/mm
0.564	0.829	7.268	3.340	0.455	1.061	5.779	3.777
0.499	1.011	6.424	4.346	0.125	1.091	4.781	2.955
0.545	0.940	7.650	3.789	0.652	0.908	8.194	4.562
0.690	0.991	8.521	6.529	0.551	0.975	7.101	3.343
0.446	1.191	5.647	5.479	0.561	0.942	7.223	3.761
0.570	0.893	7.331	3.682	0.699	0.888	8.592	5.433
0.387	1.066	4.665	2.433	0.396	1.036	4.827	3.527
0.481	1.063	6.167	3.093	0.556	0.835	7.162	4.371
0.473	1.112	6.046	4.002	0.364	1.128	4.256	2.965
0.425	1.043	5.315	4.088	0.244	1.114	7.024	3.072
0.252	0.957	2.034	2.358	0.657	0.852	8.240	4.194
0.603	0.895	7.705	6.585	0.341	1.183	3.841	4.362
0.287	1.019	5.499	3.811	0.507	1.048	6.540	4.324
0.551	0.908	7.102	4.387	0.523	0.852	6.755	3.571
0.707	0.906	8.651	3.386	0.602	1.029	7.694	4.335
0.535	0.929	6.907	3.756	0.253	0.995	2.065	2.320
0.467	0.919	5.970	3.339	0.452	0.870	5.731	4.230
0.366	0.849	4.301	2.508	0.575	0.877	7.395	4.269
0.534	0.963	6.896	3.361	0.076	1.362	0.914	2.681
0.463	1.124	5.903	5.865	0.490	1.024	6.298	3.351
0.466	1.187	5.950	4.244	0.394	0.806	4.784	3.534
0.526	1.132	6.792	4.448	0.663	0.887	8.292	3.561
0.653	0.874	8.206	3.714	0.689	0.966	8.509	3.247
0.360	1.124	7.220	2.443	0.438	0.822	5.515	4.361
0.406	1.010	4.994	5.576	0.585	0.985	7.506	4.307

MTVDI	SI	GD/m	SET/mm	盐分实测值/(g/kg)	盐分预测值/(g/kg)
0.381	1.266	4.567	3.546	26.777	16.188
0.452	0.870	5.731	2.229	22.459	7.294
0.295	1.129	6.362	3.122	51.954	32.565
0.446	0.884	5.640	4.032	2.247	3.769
0.531	0.831	6.848	3.190	1.249	2.100
0.597	0.935	7.642	3.648	1.454	1.185
0.659	1.057	8.260	4.003	2.543	0.824
0.508	0.824	6.546	3.785	0.862	2.049
0.313	0.807	3.293	3.506	6.360	14.040
0.566	0.922	7.293	4.687	1.807	1.080
0.466	0.822	5.942	3.991	2.749	2.819
0.465	1.133	5.939	2.205	17.086	10.271
0.765	1.147	9.034	4.056	1.308	0.575
0.448	0.987	5.670	3.843	4.217	4.834
0.229	1.046	6.834	3.026	46.748	40.194
0.423	1.163	5.271	4.599	1.366	6.283
0.485	0.986	6.229	5.950	0.749	1.490
0.638	0.859	8.057	3.842	0.720	0.797
0.575	0.999	7.399	3.605	4.127	1.575
0.515	1.126	6.638	5.632	1.014	1.606
0.639	0.927	8.075	3.562	3.952	0.897
0.558	1.029	7.195	3.648	0.661	1.900
0.516	1.042	8.253	4.311	2.424	2.697
0.666	1.004	5.064	4.367	1.601	0.620
0.466	1.161	5.954	4.044	1.455	5.087
0.610	0.884	7.784	3.167	5.714	1.156
0.514	0.993	6.627	3.695	1.131	2.687
0.755	0.935	8.978	4.472	1.366	0.531
0.422	1.166	5.259	4.062	4.555	7.920
0.507	1.048	6.540	4.219	0.984	2.558

土壤盐渍化等级	盐分质量分数/（g/kg）	耐盐作物生长及减产状况
极轻	<3.00	作物正常生长,不减产
弱盐化	3.00~6.00	作物生长稍受限制,减产≤20%
中盐化	6.00~10.00	作物生长中度限制,减产20~50%
强盐化	10.00~22.00	作物生长严重抑制,减产50~80%
盐土	>22.00	农作物不能生长

基于神经网络模型的干旱区绿洲土壤盐渍化评价分析

Evaluation and Analysis of Soil Salinization in the Arid Zones based on Neural Network Model

RichHTML

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 15

参考文献 27

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	范兰馨, 吴艳红, 迟皓婧, 郑思齐, 闫家恒, 任永康, 孙忠华. 暖湿化下西北地区水体变化趋势遥感监测[J]. 地球信息科学学报, 2023, 25(9): 1842-1854.
[2]	邢子瑶, 董芯蕊, 昝糈莉, 杨帅, 黄梓焓, 刘哲, 张晓东. 融合VGI和遥感等多源数据的洪涝范围提取与模拟方法[J]. 地球信息科学学报, 2023, 25(9): 1869-1881.
[3]	韩宝辉, 赵起超, 常荣, 李笑萌, 颜克勤, 付启铭. 叶绿素a浓度反演模型：堆栈自编码器粒子群优化BP神经网络[J]. 地球信息科学学报, 2023, 25(9): 1882-1893.
[4]	张俊瑶, 杨晓梅, 王志华, 杨海坤, 张博淳, 万庆, 雷梅. 绿色发展理念视角下内蒙古煤矿区格局演变分析[J]. 地球信息科学学报, 2023, 25(8): 1655-1668.
[5]	曹煜, 方秀琴, 杨露露, 蒋心远, 廖美玉, 任立良. 基于随机森林的西辽河流域CCI土壤湿度降尺度研究[J]. 地球信息科学学报, 2023, 25(8): 1669-1681.
[6]	张寒博, 李彤, 李晓芳, 邓滢, 邓应彬, 荆文龙, 胡义强, 李勇, 杨骥. 无人机遥感和GWR结合的水华短时预测方法[J]. 地球信息科学学报, 2023, 25(8): 1682-1698.
[7]	林娜, 何静, 王斌, 唐菲菲, 周俊宇, 郭江. 结合植被光谱特征与Sep-UNet的城市植被信息智能提取方法[J]. 地球信息科学学报, 2023, 25(8): 1717-1729.
[8]	刘文宋, 张仲英, 郑琳, 郭风成. 基于改进HLT与深度学习的双时相PolSAR洪涝灾害监测新方法[J]. 地球信息科学学报, 2023, 25(8): 1730-1745.
[9]	吴敏, 张明达, 李盼盼, 张勇健. 面向多源遥感影像数据的溯源模型研究[J]. 地球信息科学学报, 2023, 25(7): 1325-1335.
[10]	令振飞, 刘涛, 杜萍, 赵丹, 陈朴一, 马天恩. 一种支持建筑群组相似模式检索的变分图卷积自编码模型[J]. 地球信息科学学报, 2023, 25(7): 1405-1417.
[11]	赵丹, 杜萍, 刘涛, 令振飞. 融合图自编码器与GRU的城市盗窃犯罪时空分布预测模型[J]. 地球信息科学学报, 2023, 25(7): 1448-1463.
[12]	金广垠, 沙恒宇, 张金雷, 黄金才. 基于路段-路口联合建模的对偶图卷积网络的行程时间估计方法[J]. 地球信息科学学报, 2023, 25(7): 1500-1513.
[13]	杨颖频, 吴志峰, 黄启厅, 骆剑承, 吴田军, 董文, 胡晓东, 肖文菊. 协同遥感与统计数据的粤西甘蔗种植分布提取及时空分析[J]. 地球信息科学学报, 2023, 25(5): 1012-1026.
[14]	刘潇, 刘智, 林雨准, 王淑香, 左溪冰. 面向遥感影像场景分类的类中心知识蒸馏方法[J]. 地球信息科学学报, 2023, 25(5): 1050-1063.
[15]	侯慧太, 蓝朝桢, 徐青. 基于卫星影像全局和局部深度学习特征检索的无人机绝对定位方法[J]. 地球信息科学学报, 2023, 25(5): 1064-1074.