No abstract

Aerial image and LiDAR data offers a great possibility for agricultural land cover mapping. Unfortunately, these images leads to shadowy pixels. Management of shadowed areas for classification without image enhancement were investigated. Image segmentation approach using three different segmentation scales were used and tested to segment the image for ground features since only the ground features are affected by shadow caused by tall features. The RGB band and intensity were the layers used for the segmentation having an equal weights. A segmentation scale of 25 was found to be the optimal scale that will best fit for the shadowed and non-shadowed area classification. The SVM using Radial Basis Function kernel was then applied to extract classes based on properties extracted from the Lidar data and orthophoto. Training points for different classes including shadowed areas were selected homogeneously from the orthophoto. Separate training points for shadowed areas were made to create additional classes to reduced misclassification. Texture classification and object-oriented classifiers have been examined to reduced heterogeneity problem. The accuracy of the land cover classification using 25 scale segmentation after accounting for the shadow detection and classification was significantly higher compared to higher scale of segmentation.

Landfills have led to some of the most intense battles over pollution that has ever been seen. With the population skyrocketing worldwide, these landfills will only become more of a public issue as time goes on. Heavy metals from several sources especially in landfills are an increasingly urgent problem because of its contribution to environmental deterioration and intensive degradation of soil microbial biodiversity. Despite the arguments over landfills in general, few or no effort was undertaken to clean up contamination of heavy metals in abandoned landfills. In our study new methods were proposed using a green technology or phytoremediation with ferrous sulfate in enhancing cleanup of heavy metal polluted landfill soils. Composite soil samples were collected near an open abandoned dump site in Cabanatuan City, Nueva Ecija, Philippines. Three rates of sulfur: 0, 40 and 80 mmol kg -1 as ferrous sulfate (26% S) was thoroughly mixed with the soil. Four healthy seedlings of mustard (Brassica juncea, L) were transplanted to each pot. Soil pH showed a decreasing trend for soils treated with 0 and 80 mmol kg -1 of sulfur (S) after 15 days (8.12 to 7.38) and after 25 days (8.56 to 7.78). Application of ferrous sulfate significantly enhanced microbial activities in contaminated soils. Average respiration rate in soil with 0 mmol kg -1 S was about 2.0 mg kg -1 CO 2 -C compared with 19.0 mg kg -1 CO 2 -C for soils amended with 80 mmol S kg -1 . Although dry matter yield and uptake of heavy metals by mustard were somewhat variable with S application, solubility of copper (Cu), zinc (Zn) and manganese (Mn) in soils was significantly (p≤0.001) increased with S application. Our study has demonstrated the beneficial outcome of green technology in combination with ferrous sulfate in cleaning up heavy metals contamination in landfills and at the same time improving soil microbial biomass following phytoremediation.

Aerial image and LiDAR data offers a great possibility for agricultural land cover mapping. Unfortunately, these images leads to shadowy pixels. Management of shadowed areas for classification without image enhancement were investigated. Image segmentation approach using three different segmentation scales were used and tested to segment the image for ground features since only the ground features are affected by shadow caused by tall features. The RGB band and intensity were the layers used for the segmentation having an equal weights. A segmentation scale of 25 was found to be the optimal scale that will best fit for the shadowed and non-shadowed area classification. The SVM using Radial Basis Function kernel was then applied to extract classes based on properties extracted from the Lidar data and orthophoto. Training points for different classes including shadowed areas were selected homogeneously from the orthophoto. Separate training points for shadowed areas were made to create additional classes to reduced misclassification. Texture classification and object-oriented classifiers have been examined to reduced heterogeneity problem. The accuracy of the land cover classification using 25 scale segmentation after accounting for the shadow detection and classification was significantly higher compared to higher scale of segmentation.

No abstract