The use of WorldView-2 satellite imagery to model urban drainage system with low impact development (LID) Techniques

Within a wide range of best management practices for stormwater management in urban areas, there has been an increasing interest in source control measures. Source controls such as low-impact development (LID) techniques are potentially attractive as retrofit options for older developed areas that lack available land to implement conventional measures such as stormwater management ponds. Hence, distributed urban drainage models requiring detailed representation of developed drainage areas should be developed to accurately estimate the benefits that LIDs may provide. This study (1) presents a two-stage classification process on a high-resolution WorldView-2 image, and (2) demonstrates how to use the extracted land cover information in the subsequent hydrologic modelling and assessment of different LIDs’ performance. The proposed two-stage classification method achieved an overall accuracy of 80.6%, whereas a traditional pixel-based achieved 68.4% in classifying the same urban area into six land cover classes. From the classification results, the hydrologic properties of micro-subcatchments were imported in the United States Environmental Protection Agency Storm Water Management Model to assess the performance of LIDs. A reduction of run-off volume 18.2% and 37.1% was found with the implementation of porous pavement and bioretention, respectively, in a typical low-rise residential area located in the city of San Clemente, California, US. The study demonstrates the use of high-resolution remote sensing image to aid in evaluating LID retrofit options, and thus benefits in situations where detailed drainage area information is not available.     

机器学习法在面向对象影像分类中的对比分析

针对如何选择遥感影像面向地理对象分类方法的问题,该文面向地理国情普查中的地表覆盖分类应用,以3个典型区域(山区、平原、城区)的多源高分辨率遥感影像为实验数据,从分类效果、分类精度等方面对比分析3种分类方法(支持向量机、决策树、随机森林)的优劣。在相同影像分割、特征提取、样本采集条件下,通过333组分类实验,得出以下规律:支持向量机分类方法稳定性强,分类速度快,但对特征数的要求高,特征数目与总体精度、地物环境之间的规律性不强,从而增加了特征提取与选择的难度,而随着特征的增加,决策树、随机森林的总体分类精度均为先升高后降低,最后趋于平衡。最后,综合随机森林对特征的优选机制和支持向量机的高分类精度,得到新的组合分类器。     

Integration of high-resolution imagery and LiDAR data for object-based classification of urban area

This paper investigates the synergistic use of high-resolution multispectral imagery and Light Detection and Ranging (LiDAR) data for object-based classification of urban area. The main contribution of this paper is the development of a semi-automated object-based and rule-based classification method. In the implemented approach, the diverse knowledge about land use/land cover classes are transformed into a set of specialized rules. Further, this paper explores supervised Gaussian Mixture Models for classification, which have been primarily used for unsupervised classification. The work is carried out on test data from two different sites. Contribution of the LiDAR data resulted in a significant improvement of overall Kappa. Accuracy assessment carried out for aforementioned classification methods shows higher overall kappa for both the study sites.     

Spectral angle mapper and object-based classification combined with hyperspectral remote sensing imagery for obtaining land use/cover mapping in a Mediterranean region

In this study, we test the potential of two different classification algorithms, namely the spectral angle mapper (SAM) and object-based classifier for mapping the land use/cover characteristics using a Hyperion imagery. We chose a study region that represents a typical Mediterranean setting in terms of landscape structure, composition and heterogeneous land cover classes. Accuracy assessment of the land cover classes was performed based on the error matrix statistics. Validation points were derived from visual interpretation of multispectral high resolution QuickBird-2 satellite imagery. Results from both the classifiers yielded more than 70% classification accuracy. However, the object-based classification clearly outperformed the SAM by 7.91% overall accuracy (OA) and a relatively high kappa coefficient. Similar results were observed in the classification of the individual classes. Our results highlight the potential of hyperspectral remote sensing data as well as object-based classification approach for mapping heterogeneous land use/cover in a typical Mediterranean setting.     

A comparative assessment between object and pixel-based classification approaches for land use/land cover mapping using SPOT 5 imagery

Abstract

Land use/land cover (LULC) classification with high accuracy is necessary, especially in eco-environment research, urban planning, vegetation condition study and soil management. Over the last decade a number of classification algorithms have been developed for the analysis of remotely sensed data. The most notable algorithms are the object-oriented K-Nearest Neighbour (K-NN), Support Vector Machines (SVMs) and the Decision Trees (DTs) amongst many others. In this study, LULC types of Selangor area were analyzed on the basis of the classification results acquired using the pixel-based and object-based image analysis approaches. SPOT 5 satellite images with four spectral bands from 2003 and 2010 were used to carry out the image classification and ground truth data were collected from Google Earth and field trips. In pixel-based image analysis, a supervised classification was performed using the DT classifier. On the other hand, object-oriented (K-NN) image analysis was evaluated using standard nearest neighbour as classifier. Subsequently SVM object-based classification was performed. Five LULC categories were extracted and the results were compared between them. The overall classification accuracies for 2003 and 2010 showed that the object-oriented (K-NN) (90.5% and 91%) performed better results than the pixel-based DT (68.6% and 68.4%) and object-based SVM (80.6% and 78.15%). In general, the object-oriented (K-NN) performed better than both DTs and SVMs. The obtained LULC classification maps can be used to improve various applications such as change detection, urban design, environmental management and zooning.     

A novel ensemble approach of bivariate statistical-based logistic model tree classifier for landslide susceptibility assessment

Abstract

This study addresses landslide susceptibility mapping (LSM) using a novel ensemble approach of using a bivariate statistical method (weights of evidence [WoE] and evidential belief function [EBF])-based logistic model tree (LMT) classifier. The performance and prediction capability of the ensemble models were assessed using the area under the ROC curve (AUROC), standard error, 95% confidence intervals and significance level P. Model performance analyses indicated that the AUROC values of the WoE–LMT ensemble model using the training and validation data-sets were 86.02 and 85.9%, respectively, whereas those of the EBF–LMT ensemble model were 88.2 and 87.8%, respectively. On the other hand, the AUC curves for the four landslide susceptibility maps indicated that the AUC values of the ensemble models of WoE–LMT (85.11 and 83.98%) and EBF–LMT (86.21 and 85.23%) could improve the performance and prediction accuracy of single WoE (84.23 and 82.46%) and EBF (85.39 and 81.33%) models for the training and validation data-sets.     

决策树结合混合像元分解的中国竹林遥感信息提取

竹林是中国亚热带地区特殊而重要的森林资源,现有方法难以实现全国范围竹林时空分布信息快速准确提取。针对此问题,本研究利用2003年、2008年、2014年MODIS NDVI、反射率产品数据和省域Landsat分类数据,提出了基于决策树结合混合像元分解的全国竹林信息提取方法。首先,通过最大似然法获取中国林地分布信息;然后,在林地信息的基础上,构建决策树模型提取中国竹林分布信息;最后,采用线性最小二乘法混合像元分解得到中国竹林丰度图,并计算竹林面积。研究结果表明:(1)最大似然法提取的3个时期中国林地信息的生产者与用户精度均在90%以上,Kappa系数均值为0.93,为竹林信息提取奠定了基础。(2)C5.0算法构建的决策树模型能够很好的提取中国竹林时空分布信息,3个时期竹林分类精度均在80%左右。(3)在混合像元分解的基础上,统计得到的全国各省竹林估算面积与清查面积具有较高的相关性,R~2分别为0.98、0.97和0.95,RMSE范围为3.92万—9.58万ha,说明估算得到全国竹林面积与实际情况较为吻合。本研究所提出基于MODIS遥感数据运用C5.0算法决策树结合混合像元分解的方法,实现了全国竹林时空分布信息的准确提取,为全国竹林资源信息动态监测及管理提供了技术手段和数据支撑。     

Assessing the utility WorldView-2 imagery for tree species mapping in South African subtropical humid forest and the conservation implications: Dukuduku forest patch as case study

Indigenous forest biome in South Africa is highly fragmented into patches of various sizes (most patches < 1 km²). The utilization of timber and non-timber resources by poor rural communities living around protected forest patches produce subtle changes in the forest canopy which can be hardly detected on a timely manner using traditional field surveys. The aims of this study were to assess: (i) the utility of very high resolution (VHR) remote sensing imagery (WorldView-2, 0.5–2 m spatial resolution) for mapping tree species and canopy gaps in one of the protected subtropical coastal forests in South Africa (the Dukuduku forest patch (ca.3200 ha) located in the province of KwaZulu-Natal) and (ii) the implications of the map products to forest conservation. Three dominant canopy tree species namely, Albizia adianthifolia, Strychnos spp. and Acacia spp., and canopy gap types including bushes (grass/shrubby), bare soil and burnt patches were accurately mapped (overall accuracy = 89.3 ± 2.1%) using WorldView-2 image and support vector machine classifier. The maps revealed subtle forest disturbances such as bush encroachment and edge effects resulting from forest fragmentation by roads and a power-line. In two stakeholders’ workshops organised to assess the implications of the map products to conservation, participants generally agreed amongst others implications that the VHR maps provide valuable information that could be used for implementing and monitoring the effects of rehabilitation measures. The use of VHR imagery is recommended for timely inventorying and monitoring of the small and fragile patches of subtropical forests in Southern Africa.     

Estimation of forest aboveground biomass from HJ1B imagery using a canopy reflectance model and a forest growth model

Accurately estimating the spatial distribution of forest aboveground biomass (AGB) is important because of its carbon budget forms part of the global carbon cycle. This paper presented three methods for obtaining forest AGB based on a forest growth model, a Multiple-Forward-Mode (MFM) method and a stochastic gradient boosting (SGB) model. A Li-Strahler geometric-optical canopy reflectance model (GOMS) with the ZELIG forest growth model was run using HJ1B imagery to derive forest AGB. GOMS-ZELIG simulated data were used to train the SGB model and AGB estimation. The GOMS-ZELIG AGB estimation was evaluated for 24 field-measured data and compared against the GOMS-SGB model and GOMS-MFM biomass predictions from multispectral HJ1B data. The results show that the estimation accuracy of the GOMS-MFM model is slightly higher than that of the GOMS-SGB model. The GOMS-ZELIG and GOMS-MFM models are considerably more accurate at estimating forest AGB in arid and semiarid regions.     

An adaptive unimodal subclass decomposition (AUSD) learning system for land use and land cover classification using high-resolution remote sensing

Land use and land cover classification is an important application of remote-sensing images. The performances of most classification models are largely limited by the incompleteness of the calibration set and the complexity of spectral features. It is difficult for models to realize continuous learning when the study area is transferred or enlarged. This paper proposed an adaptive unimodal subclass decomposition (AUSD) learning system, which comprises two-level iterative learning controls: The inner loop separates each class into several unimodal Gaussian subclasses; the outer loop utilizes transfer learning to extend the model to adapt to supplementary calibration set collected from enlarged study areas. The proposed model can be efficiently adjusted according to the variability of spectral signatures caused by the increasingly high-resolution imagery. The classification result can be obtained using the Gaussian mixture model by Bayesian decision theory. This AUSD learning system was validated using simulated data with the Gaussian distribution and multi-area SPOT-5 high-resolution images with 2.5-m resolution. The experimental results on numerical data demonstrated the ability of continuous learning. The proposed method achieved an overall accuracy of over 90% in all the experiments, validating the effectiveness as well as its superiority over several widely used classification methods.     

A GEOBIA framework for the implementation of national and international forest definitions using very high spatial resolution optical satellite data

In recent decades, there is an increasing need for harmonised and accurate information on the status and extent of forests. However, delineating the extent of forest areas is a complex task, since the existence of more than 100 definitions of forest worldwide causes considerable discrepancies in forested area estimates. The aim of this work was to examine the potential of geographic object based image analysis (GEOBIA) and very high spatial resolution imagery to discriminate forest areas following two different definitions of forest in northern Greece. In particular, we examined the definition of forest under the Greek law as well as the United Nations Food and Agricultural Organisation definition. Our findings suggest that the developed GEOBIA approach not only performed remarkably well for the discrimination of forest areas but also allowed to estimate rapidly and reliably forest extents when the two aforementioned forest definitions were employed.     

WorldView-2影像林地信息提取的研究与实现

林地信息的获取具有重要意义,可广泛应用于城市规划编制、林地资源分析、水土流失治理等领域。本文基于WorldView-2影像,在研究分割与对象特征的基础上,采用面向对象方法,实现了林地信息提取,其用户精度达到94%,制图精度达到97.2%。然后,将像元二分模型应用于林地类对象,计算其植被覆盖度。试验表明,面向对象方法能高效、准确、经济地提取林地信息;基于林地类对象计算的植被覆盖度能较好地表征植被覆盖情况。     

Integration of WorldView-2 and airborne LiDAR data for tree species level carbon stock mapping in Kayar Khola watershed,Nepal

Integration of WorldView-2 satellite image with small footprint airborne LiDAR data for estimation of tree carbon at species level has been investigated in tropical forests of Nepal. This research aims to quantify and map carbon stock for dominant tree species in Chitwan district of central Nepal. Object based image analysis and supervised nearest neighbor classification methods were deployed for tree canopy retrieval and species level classification respectively. Initially, six dominant tree species (Shorea robusta, Schima wallichii, Lagerstroemia parviflora, Terminalia tomentosa, Mallotus philippinensis and Semecarpus anacardium) were able to be identified and mapped through image classification. The result showed a 76% accuracy of segmentation and 1970.99 as best average separability. Tree canopy height model (CHM) was extracted based on LiDAR’s first and last return from an entire study area. On average, a significant correlation coefficient (r) between canopy projection area (CPA) and carbon; height and carbon; and CPA and height were obtained as 0.73, 0.76 and 0.63, respectively for correctly detected trees. Carbon stock model validation results showed regression models being able to explain up to 94%, 78%, 76%, 84% and 78% of variations in carbon estimation for the following tree species: S. robusta, L. parviflora, T. tomentosa, S. wallichii and others (combination of rest tree species).     

Monitoring grass nutrients and biomass as indicators of rangeland quality and quantity using random forest modelling and WorldView-2 data

Land use and climate change could have huge impacts on food security and the health of various ecosystems. Leaf nitrogen (N) and above-ground biomass are some of the key factors limiting agricultural production and ecosystem functioning. Leaf N and biomass can be used as indicators of rangeland quality and quantity. Conventional methods for assessing these vegetation parameters at landscape scale level are time consuming and tedious. Remote sensing provides a bird-eye view of the landscape, which creates an opportunity to assess these vegetation parameters over wider rangeland areas. Estimation of leaf N has been successful during peak productivity or high biomass and limited studies estimated leaf N in dry season. The estimation of above-ground biomass has been hindered by the signal saturation problems using conventional vegetation indices. The objective of this study is to monitor leaf N and above-ground biomass as an indicator of rangeland quality and quantity using WorldView-2 satellite images and random forest technique in the north-eastern part of South Africa. Series of field work to collect samples for leaf N and biomass were undertaken in March 2013, April or May 2012 (end of wet season) and July 2012 (dry season). Several conventional and red edge based vegetation indices were computed. Overall results indicate that random forest and vegetation indices explained over 89% of leaf N concentrations for grass and trees, and less than 89% for all the years of assessment. The red edge based vegetation indices were among the important variables for predicting leaf N. For the biomass, random forest model explained over 84% of biomass variation in all years, and visible bands including red edge based vegetation indices were found to be important. The study demonstrated that leaf N could be monitored using high spatial resolution with the red edge band capability, and is important for rangeland assessment and monitoring.     

Mapping of forest tree distribution and estimation of forest biodiversity using Sentinel-2 imagery in the University Research Forest Taxiarchis in Chalkidiki,Greece

Abstract

The aim of this study is to investigate the potential of Sentinel-2 imagery for the identification and determination of forest patches of particular interest, with respect to ecosystem integrity and biodiversity and to produce a relevant biodiversity map, based on Simpson’s diversity index in Taxiarchis university research forest, Chalkidiki, North Greece. The research is based on OBIA being developed on to bi-temporal summer and winter Sentinel-2 imagery. Fuzzy rules, which are based on topographic factors, such as terrain elevation and slope for the distribution of each tree species, derived from expert knowledge and field observations, were used to improve the accuracy of tree species classification. Finally, Simpson’s diversity index for forest tree species, was calculated and mapped, constituting a relative indicator for biodiversity for forest ecosystem organisms (fungi, insects, birds, reptiles, mammals) and carrying implications for the identification of patches prone to disturbance or that should be prioritized for conservation.     

Testing the reliability and stability of the internal accuracy assessment of random forest for classifying tree defoliation levels using different validation methods

In this study, the strength and reliability of internal accuracy estimate built in random forest (RF) ensemble classifier was evaluated. Specifically, we compared the reliability of the internal validation methods of RF with independent data-sets of different splitting options for defoliation classification. Furthermore, we set out to statistically validate the best independent split option for image classification using RF and multispectral Rapideye imagery. Results show that the internal accuracy measure yields comparable results with those derived from an independent test data-set. More important, it was observed that the errors produced by the internal validation methods of RF were relatively stable as statistically shown by the lower confidence interval obtained as compared to the independent test data. Results also showed that the 70–30% split option had the lowest mean standard errors (0.2351) and hence highest accuracy when compared to the other split options. The study confirms the reliability and stability of the internal bootstrapping estimate of accuracy built within the random forest algorithm.     

水稻冠层氮素含量光谱反演的随机森林算法及区域应用

利用地面实测数据构建高精度的水稻冠层氮素含量光谱反演点模型并将其进行尺度转换,实现了水稻冠层氮素含量准实时、大区域监测。以氮素光谱敏感指数作为输入变量,冠层氮素含量数据为输出变量,利用随机森林算法构建水稻冠层氮素含量高光谱反演模型,并用苏州市水稻农田验证区数据,检验模型的普适性和有效性;利用准同步的Hyperion数据,采用对输入、输出变量进行线性变换的简单尺度转换方法实现了点模型的区域应用。结果表明:基于随机森林算法的水稻冠层氮素含量高光谱反演模型可解释、所需样本少、不会过拟合、精度高(模型在实验区的预测精度为R2=0.82,验证区检验精度为R2=0.73)且具有普适性;点模型基于高光谱遥感卫星影像和尺度转换进行区域应用,精度较高(R2=0.81)。     

Creating high-resolution bare-earth digital elevation models (DEMs) from stereo imagery in an area of densely vegetated deciduous forest using combinations of procedures designed for lidar point cloud filtering

For areas of the world that do not have access to lidar, fine-scale digital elevation models (DEMs) can be photogrammetrically created using globally available high-spatial resolution stereo satellite imagery. The resultant DEM is best termed a digital surface model (DSM) because it includes heights of surface features. In densely vegetated conditions, this inclusion can limit its usefulness in applications requiring a bare-earth DEM. This study explores the use of techniques designed for filtering lidar point clouds to mitigate the elevation artifacts caused by above ground features, within the context of a case study of Prince William Forest Park, Virginia, USA. The influences of land cover and leaf-on vs. leaf-off conditions are investigated, and the accuracy of the raw photogrammetric DSM extracted from leaf-on imagery was between that of a lidar bare-earth DEM and the Shuttle Radar Topography Mission DEM. Although the filtered leaf-on photogrammetric DEM retains some artifacts of the vegetation canopy and may not be useful for some applications, filtering procedures significantly improved the accuracy of the modeled terrain. The accuracy of the DSM extracted in leaf-off conditions was comparable in most areas to the lidar bare-earth DEM and filtering procedures resulted in accuracy comparable of that to the lidar DEM.     

A comparison of geographic datasets and field measurements to model soil carbon using random forests and stepwise regressions (British Columbia,Canada)

We used geographic datasets and field measurements to examine the mechanisms that affect soil carbon (SC) storage for 65 grazed and non-grazed pastures in southern interior grasslands of British Columbia, Canada. Stepwise linear regression (SR) modeling was compared with random forest (RF) modeling. Models produced with SR performed better than those produced using RF models (r² = 0.56–0.77 AIC = 0.16–0.30 for SR models; r² = 0.38–0.53 and AIC = 0.18–0.30 for RF models). The factors most significant when predicting SC were elevation, precipitation, and the normalized difference vegetation index (NDVI). NDVI was evaluated at two scales using: (1) the MOD 13Q1 (250 m/16-day resolution) NDVI data product from the moderate resolution imaging spectro-radiometer (MODIS) (NDVI_MODIS), and (2) a handheld multispectral radiometer (MSR, 1 m resolution) (NDVI_MSR) in order to understand the potential for increasing model accuracy by increasing the spatial resolution of the gridded geographic datasets. When NDVI_MSR data were used to predict SC, the percentage of the variance explained by the model was greater than for models that relied on NDVI_MODIS data (r² = 0.68 for SC for non-grazed systems, modeled with SR based on NDVI_MODIS data; r² = 0.77 for SC for non-grazed systems, modeled with SR based on NDVI_MSR data). The outcomes of this study provide the groundwork for effective monitoring of SC using geographic datasets to enable a carbon offset program for the ranching industry.