中国沙漠 ›› 2016, Vol. 36 ›› Issue (4): 1079-1086.DOI: 10.7522/j.issn.1000-694X.2015.00067

• 生物与土壤 • 上一篇    下一篇


丁建丽1, 陈文倩1, 陈芸2   

  1. 1. 新疆大学 资源与环境科学学院/绿洲生态教育部重点实验室, 新疆 乌鲁木齐 830046;
    2. 澳大利亚联邦科学与工业研究组织水土资源研究所, 澳大利亚, 堪培拉 VIC 3169
  • 收稿日期:2015-12-03 修回日期:2016-01-08 出版日期:2016-07-20 发布日期:2016-07-20
  • 作者简介:丁建丽(1974-),男,山东成武人,博士,教授,主要从事干旱区遥感与GIS应用研究
  • 基金资助:

Soil Salinization Disaster Warning in Arid Zones: A case study in the Ugan-Kuqa Oasis

Ding Jianli1, Niu Zengyi1, Li Yanhua2   

  1. 1. College of Resources and Environment Science/MOE Key Laboratory of Oasis Ecosystem, Xinjiang University, Urumqi 830046, China;
    2. CSIRO Land and W ater of Australia, V IC3169, Canberra, Australia
  • Received:2015-12-03 Revised:2016-01-08 Online:2016-07-20 Published:2016-07-20

摘要: 针对中国西北干旱区普遍存在的土壤盐渍化,以渭干河-库车河绿洲TM影像数据,建立BP神经网络结合Adaboost算法的土壤盐渍化预警度评价模型。首先,根据研究区实际情况设置该模型的4个预警指标(地下水埋深、海拔、盐分指数、归一化干旱指数),分别提取其连续表面信息,结合BP神经网络作为弱预测器进行预测,将通过不同训练集得到的弱预测器结果结合成强预测器。在利用该模型训练样本时,依据各评价因子对分类结果的贡献率调整其权重,预测的结果能客观反映每个评价因子对该地区土壤盐渍化的贡献程度。结果表明,研究区警情总体情况较严重,绿洲北部内部耕地周围的荒地以及含水量少的区域,盐渍化危险度较高。

关键词: 干旱区, 盐渍化, 预警, BP, Adaboost预测器

Abstract: Aiming at the prevailing northwest arid zone of soil salinization, the paper selected the Ugan-Kuqa River Oasis as studied area and TM image as data source to establish BP neural network combined with Adaboost algorithm evaluation soil salinization warning model. First, according to the actual conditions of the area set up four warning indicators of the model: groundwater depth, elevation, salinity index, normalized Drought Index, and extracted its continuous surface information, made BP neural network as a weak predictor to predict, different training obtained results are combined into a strong predictor when using the model of training samples, according to the classification results of each evaluation factor in the share of the contribution rate to adjust their weights, the predicted outcome will be fair objectively reflect each evaluation factor's contribution for the soil salinization in the region, the experimental results show that the overall situation in the study area is more serious alarm, wasteland and water content inside a small area of arable land around the northern oasis, salinization have hazard higher degree. This paper from the point of view of soil salinization warning to conduct a preliminary study and lay a foundation for further study in the future salinization warning.

Key words: arid zone, salinization, warning, BP, Adaboost predictor