共查询到20条相似文献，搜索用时 203 毫秒
1.
2.
运用分类树进行土壤类型自动制图的研究 总被引：1，自引：0，他引：1
提供了一种基于机器学习的方法来自动建立针对土壤资源制图的规则库。以浙江省龙游县研究区为例,将已有的土壤图与地质图、土地利用现状图、DEM及其派生属性、双时相的TM卫星数据相结合,使用分类树算法从训练数据中生成该地区土壤制图的规则知识,并进行了研究区土壤类型的知识分类。这种建立土壤自动制图知识库的方法要比传统的知识获取方法更为简便易行。精度评价结果表明,所建立的知识库对于研究区的大部分土壤类型的预测是可行的。 相似文献
3.
There is increasing interest in developing automatic procedures to segment landscapes into soil spatial entities that replace conventional, expensive manual procedures for delineating and classifying soils. Geographic object-based image analysis (GEOBIA) partitions remote sensing imagery or digital elevation models into homogeneous image objects based on image segmentation. We used an object-based methodology for the detailed delineation and classification of soil types using digital maps of topography and vegetation as soil covariates, based on the Random Forests (RF) classifier. We compared the object-based method's results with those of a pixel-based classification using the same classifier. We used 18 digital elevation model derivatives and 5 remote sensing indices that were related to vegetation cover and soil. Using 171 soil profiles with their associated environmental variable values, the RF method was used to identify the most important soil type predictors for use in the segmentation process. A stack of raster-geodatasets corresponding to the selected predictors was segmented using a multi-resolution segmentation algorithm, which resulted in homogeneous objects related to soil types. These objects were further classified as soil types using the same method, RF. We also conducted a pixel-based classification using the same classifier and soil profiles, and the resulting maps were assessed in terms of their accuracy using 30% of the soil profiles for validation. We found that GEOBIA was an effective method for soil type mapping, and was superior to the pixel-based approach. The optimized object-based soil map had an overall accuracy of 58%, which was 10% higher than that of the optimized pixel-based map. 相似文献
4.
利用人工神经网络以及相关地形属性绘制数字土壤地图 总被引：2，自引：0，他引：2
M. BAGHERI BODAGHABADI J. A. MART&#NEZ-CASASNOVAS M. H. SALEHI J. MOHAMMADI I. ESFANDIARPOOR BORUJENI N. TOOMANIAN A. GANDOMKAR 《土壤圈》2015,25(4):580-591
Detailed soil surveys involve costly and time-consuming work and require expert knowledge. Since soil surveys provide information to meet a wide range of needs, new methods are necessary to map soils quickly and accurately. In this study, multilayer perceptron artificial neural networks (ANNs) were developed to map soil units using digital elevation model (DEM) attributes. Several optimal ANNs were produced based on a number of input data and hidden units. The approach used test and validation areas to calculate the accuracy of interpolated and extrapolated data. The results showed that the system and level of soil classification employed had a direct effect on the accuracy of the results. At the lowest level, smaller errors were observed with the World Reference Base (WRB) classification criteria than the Soil Taxonomy (ST) system, but more soil classes could be predicted when using ST (7 soils in the case of ST vs. 5 with WRB). Training errors were below 11% for all the ANN models applied, while the test error (interpolation error) and validation error (extrapolation error) were as high as 50% and 70%, respectively. As expected, soil prediction using a higher level of classification presented a better overall level of accuracy. To obtain better predictions, in addition to DEM attributes, data related to landforms and/or lithology as soil-forming factors, should be used as ANN input data. 相似文献
5.
基于支持向量机的典型冻土区土壤制图研究 总被引：6，自引：0，他引：6
基于青藏高原大片连续多年冻土分布的东部边缘,青海省兴海县温泉地区的野外调查数据,通过对研究区遥感数据的分析,开展了土壤制图方法的探讨。以成土因素学说和土壤-景观模型理论为基础,筛选土壤分类潜在变量,在不同的变量组合下运用支持向量机(SVM)的方法建立土壤-景观模型,对整个研究区进行预测性分类。为了更好地检验该方法的有效性,采用五折交叉方式进行结果的验证。并通过对比不同变量组合的交叉验证结果和分布模拟结果图,确定了适合典型冻土区土壤分类的环境变量组合,以较少的样本知识较好地预测该区土壤类型的空间分布。 相似文献
6.
自动土壤图基于知识的分类 总被引：7，自引：0，他引：7
A machine-learning approach was developed for automated building of knowledge bases for soil resources mapping by using a classification tree to generate knowledge from training data. With this method, building a knowledge base for automated soil mapping was easier than using the conventional knowledge acquisition approach. The knowledge base built by classification tree was used by the knowledge classifier to perform the soil type classification of Longyou County, Zhejiang Province, China using Landsat TM bi-temporal images and GIS data. To evaluate the performance of the resultant knowledge bases, the classification results were compared to existing soil map based on a field survey. The accuracy assessment mad maalysis of the resultant soil maps suggested that the knowledge bases built by the machine-learning method was of good quality for mapping distribution model of soll classes over the study area. 相似文献
7.
获取准确的土壤-环境关系是数字土壤制图的关键,目前遥感影像已作为环境因子应用于土壤-环境知识的建立过程,但单幅遥感影像所包含的光谱信息差异难以将不同土壤类型区分开来。因此本文提出了一种基于多时相遥感影像的土壤制图方法：选取红安县滠水河流域为研究区,以母质类型图、等高线数据和多时相哨兵二号遥感影像为基础,提取与土壤形成有关的环境因子,通过随机森林算法获取土壤-环境关系,预测研究区各土壤类型的空间分布并成图,利用野外实地分层采样点验证推理图的精度。结果表明：推理土壤图总体分类精度高达86%,与原始土壤图对比,各土壤类型的空间分布具有一定相似性,展现了更为详细的空间细节信息,该研究成果可为更新土壤图工作提供新方法。 相似文献
8.
Digital soil mapping as a tool to generate spatial soil information provides solutions for the growing demand for high‐resolution soil maps worldwide. Even in highly developed countries like Germany, digital soil mapping becomes essential due to the decreasing, time‐consuming, and expensive field surveys which are no longer affordable by the soil surveys of the individual federal states. This article summarizes the present state of soil survey in Germany in terms of digitally available soil data, applied digital soil mapping, and research in the broader field of pedometrics and discusses future perspectives. Based on the geomorphologic conditions in Germany, relief is a major driving force in soil genesis. This is expressed by the digital–soil mapping research which highlights the great importance of digital terrain attributes in combination with information on parent material in soil prediction. An example of digital soil mapping using classification trees in Thuringia is given as an introduction in digital soil‐class mapping based on correlations to environmental covariates within the scope of the German classification system. 相似文献
9.
S&#;rgio H. G. SILVA David C. WEINDORF Wilson M. FARIA Leandro C. PINTO Michele D. MENEZES Luiz R. G. GUILHERME Nilton CURI 《土壤圈》2021,31(4):615-626
Portable X-ray fluorescence (pXRF) spectrometry and magnetic susceptibility (MS) via magnetometer have been increasingly used with terrain variables for digital soil mapping. However, this methodology is still emerging in many countries with tropical soils. The objective of this study was to use proximal soil sensor data associated with terrain variables at varying spatial resolutions to predict soil classes using the Random Forest (RF) algorithm. The study was conducted on a 316-ha area featuring highly variable soil classes and complex soil-landscape relationships in Minas Gerais State, Brazil. The overall accuracy and Kappa index were evaluated using soils that were classified at 118 sites, with 90 being used for modeling and 28 for validation. Digital elevation models (DEMs) were created at 5-, 10-, 20-, and 30-m resolutions using contour lines from two sources. The resulting DEMs were processed to generate 12 terrain variables. Total Fe, Ti, and SiO2 contents were obtained using pXRF, with MS determined via a magnetometer. Soil class prediction was performed using the RF algorithm. The quality of the soil maps improved when using only the five most important covariates and combining proximal sensor data with terrain variables at different spatial resolutions. The finest spatial resolution did not always provide the most accurate maps. The high soil complexity in the area prevented highly accurate predictions. The most important variables influencing the soil mapping were MS, Fe, and Ti. Proximal sensor data associated with terrain information were successfully used to map Brazilian soils at variable spatial resolutions. 相似文献
10.
Clovis Grinand Dominique Arrouays Bertrand Laroche Manuel Pascal Martin 《Geoderma》2008,143(1-2):180-190
This paper aims to investigate the potential of using soil-landscape pattern extracted from a soil map to predict soil distribution at unvisited location. Recent machine learning advances used in previous studies showed that the knowledge embedded within soil units delineated by experts can be retrieved and explicitly formulated from environmental data layers However, the extent to which the models can yield valid prediction has been little studied. Our approach is based on a classification tree analysis which has underwent a recent statistics advance, namely, stochastic gradient boosting. We used an existing soil-landscape map to test our methodology. Explanatory variables included classical terrain factors (elevation, slope, curvature plan and profile, wetness index, etc.), various channels and combinations of channels from LANDSAT ETM imagery, land cover and lithology maps. Overall classification accuracy indexes were calculated under two validation schemes, either taken within the training area or from a separated validation area. We focused our study on the accuracy assessment and testing of two modelling parameters: sampling intensity and spatial context integration. First, we observed strong differences in accuracy between the training area and the extrapolated area. Second, sampling intensity, in proportion to the class extent, did not largely influence the classification accuracy. Spatial context integration by the use of a mean filtering algorithm on explanatory variables increased the Kappa index on the extrapolated area by more than ten points. The best accuracy measurements were obtained for a combination of the raw explanatory dataset with the filtered dataset representing regional trend. However, the predictive capacity of models remained quite low when extrapolated to an independent validation area. Nevertheless, this study offers encouragement for the success of extrapolating soil patterns from existing soil maps to fill the gaps in present soil map coverage and to increase efficiency of ongoing soil survey. 相似文献
11.
基于土壤-环境关系的更新传统土壤图研究 总被引：4，自引：0，他引：4
传统土壤图是流域管理、生态水文模型所需土壤空间分布信息的主要数据源。然而,受传统制图技术和基础数据质量所限,传统土壤图的空间详细度和属性精确度并不高。随着地理信息技术的发展,如何利用可获取的高质量空间数据和现代空间分析技术来更新传统土壤图显得十分必要。基于传统土壤图中的土壤多边形与通过模糊聚类所得环境因子组合之间存在着对应关系这一假设,本文提出了一种从传统土壤图中提取土壤-环境关系知识并利用该知识更新传统土壤图的方法。该方法包括四个步骤:对环境数据进行模糊c均值聚类获取环境因子组合;利用传统土壤图建立环境因子组合与土壤类型间的对应关系;提取土壤-环境关系知识;进行土壤推理制图。将该方法应用于加拿大New B runsw ick省的W akefield研究区,以更新该区现有的1∶20 000的传统土壤图。应用结果表明:更新后的数字土壤图显示了更详细的空间分布信息;经野外独立验证点验证,所得土壤图(制图单元为土壤组合-排水等级)精度高出原土壤图约20%。因此,该方法是一种有效的更新传统土壤图的方法,可增加土壤图的空间详细度、提高土壤图的属性精确度。 相似文献
12.
对土壤景观格局进行的研究多是基于发生分类土壤图或通过参比转换得到的系统分类土壤图,尚无通过土壤系统分类调查直接得到的土壤图为基础进行相关研究的报道。本文依据目前可获得的我国西北黑河流域中游的20世纪80年代形成的发生分类土壤图和2012年及2013年通过系统调查采样形成的1︰50万系统分类土壤图,进行土壤景观格局分析对比。结果表明:无论系统分类还是发生分类,从类型水平来看,土壤的破碎化程度不高,被分割程度小、连通性高,土壤类型斑块形状偏简单;从景观水平来看,景观异质性较大,土壤类型数目较多,各土壤类型所占比例较均匀,土壤类型具有一定程度的积聚,土壤类型的连通度较高。与发生分类土壤图相比,系统分类的土壤类型斑块数较多,多样性指数和均匀度指数较高,蔓延度指数较低,说明在一定尺度和区域上,系统分类能更多地反映土壤类型空间上的差异,制图精度更高。 相似文献
13.
对全国第二次土壤普查中土类、亚类划分及其调查制图的辨析 总被引：1，自引：1，他引：1
按照中国发生分类对新采集的68个北京市山区的土壤剖面进行了分类命名,并与剖面点所在土壤普查图上的分类名称进行比较,结果是只有18个剖面的分类名称一致。造成分类名称不一致的原因:1发生分类以区域典型土壤剖面分类命名,而区域内很多土壤不同于典型土壤剖面;2发生分类往往以现代生物气候带为主要分类标准命名区域土壤,而不是根据土壤性质;3分类不一致的最大原因可能是制图精度不够。研究认为,土壤分类必须依据土壤性质本身,而不是土壤形成因素;采取野外单土壤性质调查制图,室内叠加单土壤性质图形成多属性图斑,根据分类系统对它们进行综合分类,以提高分类制图精度。 相似文献
14.
Procedures for automated predictive thematic mapping were developed and applied to project areas totaling more than 3 million ha of forested land in British Columbia, Canada. The effective scale of mapping was 1:20,000 using data at a grid resolution of 25 m. The methods can be described as a form of automated feature extraction or object recognition where the objects of interest consist of ecological site types. The methods implement a hybrid of automated, semi-automated and manual procedures that develop and apply heuristic, rule-based conceptual models of ecological-landform relationships. The methods rely heavily upon terrain derivatives extracted from available digital elevation models (DEMs) in addition to satellite imagery and manually digitized maps of ancillary environmental conditions. The primary input has been the BC provincial Terrain Resource Information Management (TRIM) digital elevation model (DEM) surfaced to a regular grid of 25 m. Other input layers include manually interpreted maps of parent material texture, depth and ecological exception classes, manually prepared maps of the spatial distribution of ecological zones of the BC Biogeoclimatic Ecosystem Classification (BEC) system and, to a limited extent, LandSat7 digital satellite imagery. The procedures do not use any field sampling to develop or train classification rules. A knowledge-based approach is used to establish classification rules which are defined and implemented using a Semantic Import (SI) Model implementation of fuzzy logic. All rules are constructed by examining and deconstructing published field guides that define the required ecological output classes and that document the current expert understanding of the conditions and criteria that control the spatial distribution of these desired output classes. An iterative, trial and error, process is used to develop, apply, evaluate and revise object recognition rules that relate ranges of values of key input data layers to an expert-assigned likelihood of occurrence for each ecological class of interest. Local expert knowledge is used at each stage to evaluate each new set of output results and to guide refinement of the fuzzy SI model classification rules. Field sample observations obtained along randomly selected closed traverses were collected following a line intercept approach and used to assess the accuracy of the final predictions of ecological classification. Application of the procedures has progressed from an initial pilot project through projects to evaluate operational scale-up to full-scale commercial application to millions of hectares. Costs have been reduced from a high of $3.50/ha to less than $0.20/ha. Rates of progress increased from 150,000 ha per person year to more than 2.0 million ha per person year. Independent assessments of map accuracy produced results superior to the highest accuracies reported for all alternatives, including traditional manual mapping methods. We conclude that we have formalized and automated many of the concepts and techniques previously used to create thematic maps of ecosystems using manual interpretation of stereo air photos and ancillary data combined with field observations. We have shown that automated feature extraction is able to capture and apply the concepts of landform control referenced by typical landform-based ecological models and classification systems. We have demonstrated that it is possible to produce accurate and cost-effective ecological-landform maps by applying fuzzy and Boolean logic and automated landform analysis procedures to widely available spatial data. 相似文献
15.
基于高分5号影像的东北典型黑土区土壤分类 总被引：1，自引：1，他引：0
高精度的土壤分类及制图结果有助于更好地制定土地环境保护和土地资源利用策略。为探究星载高光谱影像实现区域尺度高精度土壤分类及制图的可能性,该研究获取东北黑土区拜泉县、明水县共计4幅高分5号(GF-5)星载高光谱遥感影像。首先,将原始反射率数据(Original Reflectance,OR)进行包络线去除处理获得去包络线数据(Continuum Removal,CR);其次,对OR和CR进行主成分分析(Principal Component Analysis,PCA)处理,分别得到反射率主成分信息(OR-PCA)和去包络线主成分信息(CR-PCA),并在OR-PCA和CR-PCA的基础上结合地形因子(Terrain,TA)。最后,OR、CR、OR-PCA、CR-PCA、OR-PCA-TA、CR-PCA-TA分别作为输入量结合随机森林分类模型,进行土壤分类并实现数字土壤制图。结果表明:1)包络线去除法可有效地提高星载高光谱土壤分类精度,与OR相比,CR的总精度提高了5.48%,Kappa系数提高了0.12。2)PCA可有效地降低高光谱数据的冗余性,提高模型的运算效率以及分类精度;与CR作为输入量相比,CR-PCA的土壤分类总精度提高了3.67%,Kappa系数提高了0.02。3)TA的引入显著提升了土壤分类精度,以CR-PCA-TA作为输入量的土壤分类精度最高,总精度为81.61%,Kappa系数为0.72,实现了高精度的土壤分类模型及土壤制图。研究结果可为大范围、高精度的土壤分类及制图提供新的思路。 相似文献
16.
半干旱沙区土类/亚类的遥感调查制图方法 总被引：1，自引：0，他引：1
传统土壤调查制图存在低时效性、低精度等问题。为了解决半干旱沙区土壤遥感调查制图问题,该文以科尔沁左翼后旗为例,基于野外实地调查和专家知识分析了半干旱沙区土壤类型分布特征与环境因素之间的关系,并探讨了基于多时相Landsat8 OLI影像数据的半干旱沙区土类/亚类遥感调查制图方法。结果表明:利用多时相Landsat8 OLI影像数据提取的归一化差异水体指数(modified normalized difference water index,MNDWI)、盐分指数(salt index,SI)、归一化差异湿度指数(normalized difference moisture index,NDMI)、归一化差异植被指数(normalized difference vegetation index,NDVI)等环境信息,可实现对沼泽土、盐碱土、草甸土、风沙土及其亚类等半干旱沙区主要土壤类型的遥感调查制图。应用本文提出的半干旱区土类/亚类遥感调查制图方法对科左后旗进行土壤遥感调查制图和精度验证,总体精度约为72.84%,Kappa系数为0.667 8。该方法可为半干旱沙区数字土壤调查制图提供思路和参考。 相似文献
17.
基于裸土期多时相遥感影像特征及最大似然法的土壤分类 总被引：1，自引：5，他引：1
运用单时相遥感数据进行土壤分类及制图,其数据本身易受到其他因素干扰而出现误差,存在一定的局限性,导致制图精度不高。为了提高制图精度,以松嫩平原林甸县为研究区,利用裸土时期多时相Landsat 8遥感影像、DEM数据和全国第二次土壤普查数据,从所有单时相遥感影像中提取出多种分类特征,按照分类特征类型进行压缩处理,得到新的多时相分类特征,将不同分类特征进行组合并分别进行最大似然法分类,得到不同分类特征组合下的土壤类型图,通过不同土壤类型图精度来判断各分类特征对于制图的影响。研究表明,该文所提取的分类特征均可以实现土壤制图,使用压缩处理后得到的多时相遥感数据分类特征完成制图的精度更高,总体精度达到91.0%,研究可为土壤精细制图提供依据。 相似文献
18.
基于环境变量的渭干河-库车河绿洲土壤盐分空间分布 总被引：5，自引：4，他引：1
土壤属性的数字制图对精准农业生产和环境保护治理至关重要。为了在大尺度上尽可能精确的监测土壤盐分空间变异性,该文使用普通克里格(ordinary kriging,OK)、地理加权回归(geographically weighted regression,GWR)和随机森林(random forest,RF)方法,结合地形、土壤理化性质和遥感影像数据等16个环境辅助变量,绘制渭干河-库车河绿洲表层土壤盐分分布图。基于决定系数(R^2)、均方根误差(RMSE)和平均绝对误差(MAE)验证模型精度。结果表明:不同方法预测的盐分分布趋势没有显著差异,大体上从研究区的西北向东南部方向增加;结合辅助变量的不同预测方法中,RF方法预测精度最高,R^2为0.74,RMSE和MAE分别为9.07和7.90 mS/cm,说明该模型可以有效地对区域尺度的土壤盐分进行定量估算;RF方法对电导率(electric conductivity,EC)低于2 mS/cm时预测精度最高,RMSE为3.96 mS/cm,很好的削弱了植被覆盖对电导率EC的影响。 相似文献
19.
WANG De-Cai ZHANG Gan-Lin PAN Xian-Zhang ZHAO Yu-Guo ZHAO Ming-Song WANG Gai-Fen 《土壤圈》2012,22(3):394-403
The use of landscape covariates to estimate soil properties is not suitable for the areas of low relief due to the high variability of soil properties in similar topographic and vegetation conditions.A new method was implemented to map regional soil texture (in terms of sand,silt and clay contents) by hypothesizing that the change in the land surface diurnal temperature difference (DTD) is related to soil texture in case of a relatively homogeneous rainfall input.To examine this hypothesis,the DTDs from moderate resolution imagine spectroradiometer (MODIS) during a selected time period,i.e.,after a heavy rainfall between autumn harvest and autumn sowing,were classified using fuzzy-c-means (FCM) clustering.Six classes were generated,and for each class,the sand (> 0.05 mm),silt (0.002-0.05 mm) and clay (< 0.002 mm) contents at the location of maximum membership value were considered as the typical values of that class.A weighted average model was then used to digitally map soil texture.The results showed that the predicted map quite accurately reflected the regional soil variation.A validation dataset produced estimates of error for the predicted maps of sand,silt and clay contents at root mean of squared error values of 8.4%,7.8% and 2.3%,respectively,which is satisfactory in a practical context.This study thus provided a methodology that can help improve the accuracy and efficiency of soil texture mapping in plain areas using easily available data sources. 相似文献
20.
SOIL CLASSIFICATION IN THE SOIL SURVEY OF ENGLAND AND WALES 总被引：2，自引：0，他引：2
B. W. AVERY 《European Journal of Soil Science》1973,24(3):324-338
The development of soil classification as a basis for soil mapping in England and Wales is briefly reviewed, and a system for future use is described. The things classified are soil profiles, and classes are defined by relatively permanent characteristics that can be observed or measured in the field, or inferred within limits from field examination by comparison with analysed samples. Profile classes are defined at four categorical levels by progressive division, and are termed major groups, groups, subgroups, and soil series respectively. Classes in the three higher categories are defined partly by the composition of the soil material and partly by the presence or absence of particular diagnostic horizons, or evidence of recent alluvial origin, within specified depths. Soil series are distinguished by other characteristics, chiefly lithologic, not differentiating in higher categories. Most of the soil groups, regarded as the principal category above the soil series, are closely paralleled in other European systems, in the U.S.D.A. system (7th Approximation with subsequent amendments), or in both. Compared with the system used hitherto, the main innovations are the use of specific soil properties to define classes at all categorical levels, and the separation at group level of classes based primarily on inherited lithologic characteristics. The soil-profile classification provides a uniform basis for identifying soil map units, considered as classes of delineated soil bodies. When a map unit is identified by the name of a profile class, it is implied that most of the soil in each delineation conforms to that class, and that unconforming inclusions belong to one or more closely related classes or occupy an insignificant proportionate area. Map units identified by land attributes not differentiating in the profile classification are termed phases. 相似文献