Texture Analysis for Mapping Tamarix parviflora Using Aerial Photographs along the Cache Creek, California

Natural color photographs were used to detect the coverage of saltcedar, Tamarix parviflora, along a 40 km portion of Cache Creek near Woodland, California. Historical aerial photographs from 2001 were retrospectively evaluated and compared with actual ground-based information to assess accuracy of the assessment process. The color aerial photos were sequentially digitized, georeferenced, classified using color and texture methods, and mosaiced into maps for field use. Eight types of ground cover (Tamarix, agricultural crops, roads, rocks, water bodies, evergreen trees, non-evergreen trees and shrubs (excluding Tamarix)) were selected from the digitized photos for separability analysis and supervised classification. Due to color similarities among the eight cover types, the average separability, based originally only on color, was very low. The separability was improved significantly through the inclusion of texture analysis. Six types of texture measures with various window sizes were evaluated. The best texture was used as an additional feature along with the color, for identifying Tamarix. A total of 29 color photographs were processed to detect Tamarix infestations using a combination of the original digital images and optimal texture features. It was found that the saltcedar covered a total of 3.96 km² (396 hectares) within the study area. For the accuracy assessment, 95 classified samples from the resulting map were checked in the field with a global position system (GPS) unit to verify Tamarix presence. The producer's accuracy was 77.89%. In addition, 157 independently located ground sites containing saltcedar were compared with the classified maps, producing a user's accuracy of 71.33%.     

A Tool for Classification and Regression Using Random Forest Methodology: Applications to Landslide Susceptibility Mapping and Soil Thickness Modeling

Classification and regression problems are a central issue in geosciences. In this paper, we present Classification and Regression Treebagger (ClaReT), a tool for classification and regression based on the random forest (RF) technique. ClaReT is developed in Matlab and has a simple graphic user interface (GUI) that simplifies the model implementation process, allows the standardization of the method, and makes the classification and regression process reproducible. This tool performs automatically the feature selection based on a quantitative criterion and allows testing a large number of explanatory variables. First, it ranks and displays the parameter importance; then, it selects the optimal configuration of explanatory variables; finally, it performs the classification or regression for an entire dataset. It can also provide an evaluation of the results in terms of misclassification error or root mean squared error. We tested the applicability of ClaReT in two case studies. In the first one, we used ClaReT in classification mode to identify the better subset of landslide conditioning variables (LCVs) and to obtain a landslide susceptibility map (LSM) of the Arno river basin (Italy). In the second case study, we used ClaReT in regression mode to produce a soil thickness map of the Terzona catchment, a small sub-basin of the Arno river basin. In both cases, we performed a validation of the results and a comparison with other state-of-the-art techniques. We found that ClaReT produced better results, with a more straightforward and easy application and could be used as a valuable tool to assess the importance of the variables involved in the modeling.     

Mapping afforestation and deforestation from 1974 to 2012 using Landsat time-series stacks in Yulin District, a key region of the Three-North Shelter region, China

The Three-North Shelter Forest Program is the largest afforestation reconstruction project in the world. Remote sensing is a crucial tool to map land use and land cover change, but it is still challenging to accurately quantify the change in forest extent from time-series satellite images. In this paper, 30 Landsat MSS/TM/ETM+ epochs from 1974 to 2012 were collected, and the high-quality ground surface reflectance (GSR) time-series images were processed by integrating the 6S atmosphere transfer model and a relative reflectance normalization algorithm. Subsequently, we developed a vegetation change tracking method to reconstruct the forest change history (afforestation and deforestation) from the time-series Landsat GSR images based on the integrated forest z-score (IFZ) model by Huang et al. (2009a), which was improved by multi-phenological IFZ models and the smoothing processing of IFZ data for afforestation mapping. The mapping result showed a large increase in the extent of forest, from 380,394 ha (14.8 % of total district area) in 1974 to 1,128,380 ha (43.9 %) in 2010. Finally, the land cover and forest change map was validated with an overall accuracy of 89.1 % and a kappa coefficient of 0.858. The forest change time was also successfully retrieved, with 22.2 % and 86.5 % of the change pixels attributed to the correct epoch and within three epochs, respectively. The results confirmed a great achievement of the ecological revegetation projects in Yulin district over the last 40 years and also illustrated the potential of the time-series of Landsat images for detecting forest changes and estimating tree age for the artificial forest in a semi-arid zone strongly influenced by human activities.     

Ecotoxicological Classification of the Berlin River System Using Bioassays in Respect to the European Water Framework Directive

Bioassays as well as biochemical responses (biomarkers) in ecosystems due to environmental stress provide us with signals (environmentally signalling) of potential damage in the environment. If these responses are perceived in this early stage in ecosystems, the eventual damage can be prevented. Once ecosystem damage has occurred, the remedial action processes for recovery could be expensive and pose certain logistical problems. Ideally, “early warning signals” in ecosystems using sensing systems of biochemical responses (biomarkers) would not only tell us the initial levels of damage, but these signals will also provide us with answers by the development of control strategies and precautionary measures in respect to the European Water Framework Directive (WFD). Clear technical guidelines or technical specifications on monitoring are necessary to establish and characterise reference conditions for use in an ecological status classification system for surface water bodies. For the Ecotoxicological Risk Assessment (ERA) of endocrine effects we used an approach of the exposure – dose – response concept. Based on the “Ecototoxicological Classification System of Sediments” that uses pT-values to classify effects in different river systems, we transferred the bio-monitoring data to the five-level ecological system of the WFD. To understand the complexity of the structure of populations and processes behind the health of populations, communities and ecosystems an ERA should establish links between natural factors, chemicals, and biological responses so as to assess causality. So, our ecological monitoring assessment has incorporated exposure & effects data.     

Using slides to test for changes in crown defoliation assessment methods part II: Application of the image analysis system CROCO

We tested whether the semi-automatic program CROCO can replace visual assessments of slides to detect changes in defoliation assessment methods. We randomly selected a series of slides of 24 Norway spruce trees with 220 field assessments made between 1986 and 1995. The slides had been randomly arranged and assessed by three experts without knowledge of the tree number or the year when the slide was taken. Defoliation scores were computed with CROCO. Each tree had thus three different defoliation scores, field assessments, photo assessments and CROCO scores.CROCO scores were less correlated with the field assessments (Spearmans rank correlation: 0.67) than were the slide assessments with the field assessments (0.79–0.83). However, CROCO was not biased against the field scores, while slide assessments systematically underestimated defoliation.In a multi-variate mixed effect model none of the variables tree overlap, tree visibility and light conditions was significant in explaining differences between slide assessors and CROCO scores. The same model applied for the differences from the field scores yielded significant effects for poor light conditions (CROCO and all assessors), for crown overlap (CROCO and one assessor) and for visibility (one assessor). We conclude, therefore, that CROCO can be used to detect past and future changes in assessment methods without bias if poor quality photographs are avoided.