In the presented study, the Sentinel-2 vegetation indices (VIs) were evaluated in context of estimating defoliation of Scots pine stands in western Poland. Regression and classification models were built based on reference data from 50 field plots and Sentinel-2 satellite images from three acquisition dates. Three machine-learning (ML) methods were tested: k-nearest neighbors (kNN), random forest (RF), and support vector machines (SVM). Regression models predicted stands defoliation with moderate accuracy. R2 values for regression models amounted to 0.53, 0.57, 0.57 for kNN, RF and SVM, accordingly. Analogically, the following values of normalized root mean squared error were obtained: 12.2%, 11.9% and 11.6%. Overall accuracies for two-class classification models were 78%, 75%, 78% for kNN, RF and SVM methods. The Green Normalized Difference Vegetation Index and MERIS Terrestrial Chlorophyll Index VIs were found to be most robust defoliation predictors regardless of the ML method. We conclude that Sentinel-2 satellite images provide useful information about forest defoliation and may contribute to forest monitoring systems.
4 November 2015 in International Journal of Geographical Information Science
Debates on the encroaching commercialization of public space by outdoor advertising highlight its possible negative impact on local quality of life and enjoyment of public spaces. These overstimulating outdoor advertisements are often considered a source of visual pollution, but cities have no standard way of measuring where it exists and its local impact, and thus cannot regulate it effectively. This study illustrates that visual pollution can be measured in a useful way by relating public opinion to the number of visible advertisements (intervisibility analysis). Using a 2.5D outdoor advertisement (OA) dataset (location and height) of a busy urban street in Lublin, Poland, this preliminary experiment translates visibility into visual pollution. It was found that streetscape views with more than seven visible OAs created visual pollution in this case study. The GIS-based methodology proposed could provide Lublin officials with a basic tool to assess and manage visual pollution, by informing permitting decisions on OAs.
In 2011 the Marshal Office of Małopolska Voivodeship decided to evaluate the vulnerability of soils to water erosion for the entire region. The quantitative and qualitative assessment of the erosion risk for the soils of the Małopolska region was done based on the USLE approach. The special work-flow of geoinformation technologies was used to fulfil this goal. A high-resolution soil map, together with rainfall data, a detailed digital elevation model and statistical information about areas sown with particular crops created the input information for erosion modelling in GIS environment. The satellite remote sensing technology and the object-based image analysis (OBIA) approach gave valuable support to this study. RapidEye satellite images were used to obtain the essential up-to-date data about land use and vegetation cover for the entire region (15,000 km2). The application of OBIA also led to defining the direction of field cultivation and the mapping of contour tillage areas. As a result, the spatially differentiated values of erosion control practice factor were used. Both, the potential and the actual soil erosion risk were assessed quantificatively and qualitatively. The results of the erosion assessment in the Małopolska Voivodeship reveal the fact that a majority of its agricultural lands is characterized by moderate or low erosion risk levels. However, high-resolution erosion risk maps show its substantial spatial diversity. According to our study, average or higher actual erosion intensity levels occur for 10.6 % of agricultural land, i.e. 3.6 % of the entire voivodeship area. In 20 % of the municipalities there is a very urgent demand for erosion control. In the next 23 % an urgent erosion control is needed. Our study showed that even a slight improvement of P-factor estimation may have an influence on modeling results. In our case, despite a marginal change of erosion assessment figures on a regional scale, the influence on the final prioritization of areas (municipalities) according to erosion control needs is visible. The study shows that, high-resolution satellite imagery and OBIA may be efficiently used for P-factor mapping and thus contribute to a refined soil erosion risk assessment.
1 November 2021 in Urban Forestry & Urban Greening
Estimation of forest stand parameters using remotely sensed data has considerable significance for sustainable forest management. Wide and free access to the collection of medium-resolution optical multispectral Sentinel-2 satellite images is very important for the practical application of remote sensing technology in forestry. This study assessed the accuracy of Sentinel-2-based growing stock volume predictive models of single canopy layer Scots pine (Pinus sylvestris L.) stands. We also investigated whether the inclusion of Sentinel-2 data improved the accuracy of models based on airborne image-derived point cloud data (IPC). A multiple linear regression (LM) and random forest (RF) methods were tested for generating predictive models. The measurements from 94 circular field plots (400 m2) were used as reference data. In general, the LM method provided more accurate models than the RF method. Models created using only Sentinel-2A images had low prediction accuracy and were characterized by a high root mean square error (RMSE%) of 35.14% and a low coefficient of determination (R2) of 0.24. Fusion of IPC data with Sentinel-2 reflectance values provided the most accurate model: RMSE% = 16.95% and R2 = 0.82. However, comparable accuracy was obtained using the IPC-based model: RMSE% = 17.26% and R2 = 0.81. The results showed that for single canopy layer Scots pine dominated stands the incorporation of Sentinel-2 satellite images into IPC-based growing stock volume predictive models did not significantly improve the model accuracy. From an operational point of view, the additional utilization of Sentinel-2 data is not justified in this context.