Building extraction has been a challenging task due to complex structures and features of various land use with matching spectral and spatial attributes in a satellite data. We attempted to extract building as features using machine-learning algorithms such as Support Vector Machine (SVM), Random Forests (RF), Artificial Neural Network (ANN) and Improved Ensemble Technique as Gradient Boosting. The techniques used increases their classification accuracies using spectral properties as well as indices such as Normalized Difference Vegetation Index (NDVI) as attributes. Extracted results through various methods, performance of three different machine learning such as Ensemble method, RF and SVM are applied and results are analyzed for their behavior in different building distribution. Different algorithms showed variations in accuracies and performance in different built-up conditions. Ensemble algorithm performed very well in all conditions followed by RF and SVM performed better in coarse resolution, while ANN performed better in high resolution and overall accuracies of all algorithms increased with better spatial resolution. Ensemble algorithm showed relatively efficient performance in regions with extensive heterogeneous features. These analyses can helpful to provide quantitative data for various stocktaking analysis and city managers for better administration capabilities.
Hydrochemical investigation was undertaken in the Kadava river basin to ascertain the groundwater quality and its suitability for drinking and irrigation purposes. In this context, forty (40) representative groundwater samples were collected from different dug/bore wells based on their importance in drinking and analyzed. Physicochemical parameters like pH, EC and TDS; cations viz., Ca, Mg, Na and K; and anions include CO3, HCO3, SO4, NO3, F, Cl were determined to authenticate the groundwater suitability for drinking. According to BIS, pH (15%), TDS (27.5%), TH (27.5%), Mg (45%), Na (15%), Cl (2.5%), NO3 (52.5%) and F (2.5%) samples exceed the permissible limit (PL); hence, unfit for drinking. The positive loading of TDS and TH is influenced by the content of Mg, Na, Cl and SO4 ions. The increased concentration of Na over Ca corresponds to the ion exchange process. The irrigation indices like SAR, Na (%), RSC, MAR, KR and SSP were considered to evaluate groundwater aptness for irrigation. According to SAR and RSC classification all groundwater samples are suitable for irrigation. MAR ratio suggests 97.5% samples are unfit for irrigation. The study advocates that, those aquifers which are awkward then particular remedial measures required prior to their beneficial use.
The main objective of the present study is to project the future scenario of land use/ land cover on the basis of their past pattern of change. Indus basin with its diverse physiography is an ideal study area. Remote sensing sources from Landsat (MSS), LISS-I and LISS-III (1985–2005), were used to assess the past land use at a scale of 1:250,000. A statistical driver-based model was used to simulate the land use scenarios for 2015 and 2025. The model output was validated by comparing the simulated maps with reference ones for 2005 and 2015. All the land use classes displayed an overall accuracy of 85–90% with the exception of the classes “built-up” and “wasteland”.
Moroccan women, like others in different parts of the world, contribute to the education of generations and the transmission of the oral heritage through tales, poems and proverbs riddles. They also uphold the physical heritage such as clothes, textile and jewellry. Since the intangible and oral heritage in Morocco varies from one area to another, focus will be put on the Imilchil area, where the festival of marriage is held. Women in this region play a key role in preserving the Amazigh cultural heritage. They are educators and models that guide the coming generations and reinforce their identity.
Extensive industrialization in the southern part of Gujarat is characterized by regional pollution of soil and water resources. In view of this, the present study has been undertaken in Ankaleshwar, one of the biggest industrial townships of India. About, 25 surface sediment /soil samples were collected from top 10 cm representing entire study area and were analyzed for heavy metals by using X-ray fluorescence spectrometer (XRF). The heavy metals concentrations were compared with the standard shale to find out pollution index (PI), results shows the significant enrichment for arsenic, moderate enrichment for Pb and minimal enrichment for metals in descending order as Fe>Mn>Cr>Ni>Co>Zn>Cu>Mo. Physico-chemical properties such as texture, cation exchange capacity, total carbonate and organic matter, as well as the percentages of the sand, silt, and clay fractions have been examined. It is observed that heavy metals like Ni, Cu, Zn, and Mo show a positive correlation with the silt size fraction. Similarly, Mn, Cr, As, and Pb show positive correlation with clay size fraction. Chemical properties like EC, CEC and organic matter have control over majority of heavy metals. High correlation with these properties suggests that higher ionic conductivity soils have high heavy metal content. The effect of these properties can be arranged in descending order as follows: EC >OM > Clay % >Silt % > CEC.