Maria Tsakiri-Strati

A Hidden Markov Models Approach for Crop Classification: Linking Crop Phenology to Time Series of Multi-Sensor Remote Sensing Data

Vegetation monitoring and mapping based on multi-temporal imagery has recently received much attention due to the plethora of medium-high spatial resolution satellites and the improved classification accuracies attained compared to uni-temporal approaches. Efficient image processing strategies are needed to exploit the phenological information present in temporal image sequences and to limit data redundancy and computational complexity. Within this framework, we implement the theory of Hidden Markov Models in crop classification, based on the time-series analysis of phenological states, inferred by a sequence of remote sensing observations. More specifically, we model the dynamics of vegetation over an agricultural area of Greece, characterized by spatio-temporal heterogeneity and small-sized fields, using RapidEye and Landsat ETM+ imagery. In addition, the classification performance of image sequences with variable spatial and temporal characteristics is evaluated and compared. The classification model considering one RapidEye and four pan-sharpened Landsat ETM+ images was found superior, resulting in a conditional kappa from 0.77 to 0.94 per class and an overall accuracy of 89.7%. The results highlight the potential of the method for operational crop mapping in Euro-Mediterranean areas and provide some hints for optimal image acquisition windows regarding major crop types in Greece.

An object-based approach for flood area delineation in a transboundary area using ENVISAT ASAR and LANDSAT TM data

The aim of this study was to develop a straightforward approach for flood area mapping in a transboundary riverbed using Geographic Object-Based Image Analysis. Weak bilateral/multilateral cooperation among neighboring countries hampers effective disaster management and mitigation activities over transboundary areas and strengthens the demand for reliable remote-sensing-derived information. Three object-based classification approaches using ENVISAT/ASAR and multi-temporal LANDSAT TM data were developed and validated for flood area delineation. The accuracy assessment of the classification results was based on oblique air photo interpretation and an area-based comparison with the official flood map. The bi-level object-based model using the Normalized Difference Water Index and the original post-flood TM bands attained 92.67% overall accuracy in inundated-areas detection, while the ENVISAT/ASAR classification was the least accurate (85.33%), probably due to the lower spatial resolution of the Synthetic Aperture Radar image. A strong agreement (92.14%) was found between the LANDSAT flood extent and the official flood map, suggesting that the proposed method has the potential to be employed in the future as a standard part of a flood crisis management process.

Analysis of Time-Series Spectral Index Data to Enhance Crop Identification Over a Mediterranean Rural Landscape

Spectral index time series can provide valuable phenological information into the classification process for the precise crop mapping, in order to reduce misclassification rates associated with low interclass and high intraclass spectral variability. Stochastic hidden Markov models (HMMs) are efficient yet computationally demanding classification approach which can simulate crop dynamics, exploiting the spectral information of their phenological states and the relations between these states. This letter aims to present a methodology which achieves accurate classification results while maintaining a low computational cost. A classification framework based on HMMs was developed, and different spectral indices were generated from the time series of Landsat ETM+ and RapidEye imagery, for modeling crop vegetation dynamics over a Mediterranean rural area, with high spatiotemporal crop heterogeneity. To further improve the HMMs indices classification, separability analysis and two different decision fusion strategies were tested. The assessment of the classification accuracy, along with an evaluation of the computational cost, indicated that the green-red vegetation index produced the most favorable results among the individual spectral indices. Although the decision fusion based on an integration of a reliability factor increased the overall accuracy by 3.1%, this came at the cost of computational time, compared to the separability analysis model which required less processing time.

Assessment and mapping of urban environmental quality using remote sensing and geospatial data

Urban environmental management is of profound importance due to increasing urban development alongside the need to develop resilient cities and sustainable urbanization strategies. Spatial explicit urban environmental quality indices can provide policy makers and the public with valuable information for urban planning and policy formation. The aim of this study is the development of a multi-component urban environmental quality index for the metropolitan area of Thessaloniki. The approach was designed to be robust and easily transferred across cities with similar characteristics. Land Surface Temperature (LST) was estimated based on multi-seasonal Landsat-8 images, while Fractional Vegetation Cover (FVC) was derived from fused Sentinel-2 images and validated using WorldView-2 very high spatial resolution imagery. In addition, several geospatial layers related to atmospheric pollution, petroleum refineries, noise pollution, urban density and distance to green infrastructures were processed within GIS environment and integrated with the satellite extracted information. A multi-criteria Analytical Hierarchical Approach (AHP) was used for integrating the sub-criteria to a final urban environmental quality index using weights from expert knowledge and literature review. The results identified extended areas in the western part of the study region as well as several hot spots in the eastern part, that local planners should develop and implement actions for improving living conditions of residents. Overall, the method proved to be viable and flexible and its application can be expanded to similar Mediterranean cities.

Assessment of Radiometric Resolution Impact on Remote Sensing Data Classification Accuracy

Improved sensor characteristics are generally assumed to increase the potential accuracy of image classification and information extraction from remote sensing imagery. However, the increase in data volume caused by these improvements raise challenges associated with the selection, storage, and processing of this data, and with the cost-effective and timely analysis of the remote sensing datasets. Previous research has extensively assessed the relevance and impact of spatial, spectral and temporal resolution of satellite data on classification accuracy, but little attention has been given to the impact of radiometric resolution. This study focuses on the role of radiometric resolution on classification accuracy of remote sensing data through different classification experiments over three different sites. The experiments were carried out using fine and low scale radiometric resolution images classified through a bagging classification tree. The classification experiments addressed different aspects of the classification road map, including among others, binary and multiclass classification schemes, spectrally and spatially enhanced images, as well as pixel and objects as units of the classification. In addition, the impact of image radiometric resolution on computational time and the information content in fineand low-resolution images was also explored. While in certain cases, higher radiometric resolution has led to up to 8% higher classification accuracies compared to lower resolution radiometric data, other results indicate that higher radiometric resolution does not necessarily imply improved classification accuracy. Also, classification accuracy of spectral indices and texture bands is not related so much to the radiometric resolution of the original remote sensing images but rather to their own radiometric resolution. Overall, the results of this study suggest that data selection and classification need not always adhere to the highest possible radiometric resolution.