Search

We evaluate the penetration depth of synthetic aperture radar (SAR) signals into the ground surface at different frequencies. We applied dielectric models (Dobson empirical, Hallikainen, and Dobson semi-empirical) on the ground surface composed of different soil types (sandy, loamy, and clayey). These models result in different penetration depths for the same set of sensors and soil properties. The Dobson semi-empirical model is more sensitive to the soil properties, followed by the Hallikainen and Dobson empirical models. We used the Dobson semi-empirical model to study the penetration depth of the upcoming NASA-ISRO synthetic aperture radar (NISAR) mission operated at the L-band (1.25 GHz) and the S-band (3.22 GHz) into the ground. We observed that depending upon the soil types, the penetration depth of the SAR signals ranges between 0 to 10 cm for the S-band and 0 to 25 cm for the L-band.

The Betwa River basin, a semi-arid catchment that has been classified as a major hotspot of groundwater depletion in Central India. The rainfall and streamflow intermittency have affected agricultural practices due to the variability of groundwater availability for irrigation. This study evaluates the spatial and temporal variations of groundwater level (GWL) in the last 25 years (1993–2018) in the catchment. We applied a nonparametric Seasonal Trend decomposition based on the Loess (STL) method to decompose the GWL time series into the seasonal, trend, and remainder components. We observed that the GWL in the northeastern regions of the basin has depleted about 3–5 mbgl in the last two decades. During the same period, the basin has experienced a reduction in the rainfall magnitude (2.07 mm/yr). We observed that the overexploitation of groundwater for irrigation and rainfall variability have greatly impacted the GWL condition in the study area. Further, if the groundwater extraction continues at present rates, the Betwa River basin may experience severe depletion in the future.

We propose a hybrid machine learning algorithm (i.e., P2CA−PSO−ANN) to model malaria outbreak in three districts (Barmer, Bikaner, and Jodhpur) of Rajasthan in the Western India. We have used different meteorological variables (i.e., relative humidity, temperature, and rainfall) as input features to predict malaria. We have also considered the combined impact of these variables through a linear data fusion. We then extract the uncorrelated information from the feature set by applying Probabilistic Principal Component Analysis (P2CA). We trained the fully connected feed-forward Artificial Neural Network (ANN) by optimising its hyperparameters iteratively through a bio-inspired optimisation algorithm (Particle Swarm Optimisation). We train and evaluate the performance of this algorithm using monthly meteorological variables from 2009 - 2012. This accurately predicts the malaria cases with the coefficient of correlation (R = 0.99), and Root Mean Square Error (RMSE = 1.76). Finally, we compare our model with different benchmark algorithms (Generalised Regression Neural Network (GRNN), Gaussian Process Regression (GPR), Support Vector Regression (SVR), Random Forest, and Radial Basis Neural Networks (RBNN)) in terms of accuracy. We observed the performance of hybrid machine learning model relatively high. This study can be used as an early warning intelligent system to predict the malaria outbreaks solely from meteorological data.