Integration of artificial intelligence with meta classifiers for the gully erosion susceptibility assessment in Hinglo river basin,Eastern India

The main aim of this study is to evaluate the gully erosion susceptibility coupling the artificial intelligence and machine learning ensemble approaches. In the present study, the multilayer perceptron neural network (MLP) was used as the base classifier and the hybrid ensemble machine learning methods i.e. Bagging and Dagging were used as the functional classifiers. The Hinglo river basin, an important tributary of the Ajay River was selected as the study area, consists with the parts of Chhotonagpur plateau and Rarh lateritic region. The study area is facing the gully erosion problems which are interrupted the growth of the agriculture. The gully erosion susceptibility maps (GESMs), prepared by MLP, MLP-Bagging and MLP-Dagging were classified into four classes such as low, moderate, high and very high susceptibility classes with the help of natural break method (NBM) in GIS environment. The very high susceptibility class covered 19.41% (MLP), 13.52% (MLP-Bagging) and 15.30% (MLP-Dagging) areas of the basin. For the evaluation and comparison of the models, receiver operating characteristics (ROC), accuracy, mean absolute error (MAE) and root mean square error (RMSE) were applied. Overall, all the gully erosion susceptibility models were performed as excellent. Integration of hybrid ensemble models with MLP has increase the accuracy of the MLP models. Among these models MLP-Dagging has achieved the highest accuracy in compare to the other models. The importance of the selected factors in the present study was assessed by the Relief-F method. The results show that the soil type factor has the highest predictive performance. Sensitivity analysis also showed soil type as most important factor. The gully erosion susceptibility maps (GESMs) are considered as the efficient tool which could be used to take the necessary steps for mitigating and controlling the soil erosion problem and sustainable environmental management and development.     

A multiobjective optimization approach to determine the parameters of stepped frequency pulse train

Frequency stepping techniques are commonly used in modern radar system to get high range resolution with the disadvantage that its autocorrelation function (ACF) yield undesirable “grating lobes”. Wider mainlobe deteriorates the range resolution capability of the waveform and higher peak sidelobe either hides the small targets or causes the false target detection. Several techniques have been used to choose the parameters of linear frequency modulated (LFM) pulse train to suppress the grating lobes without paying much attention to the mainlobe width and peak sidelobe level. In this paper a multiobjective optimization (Nondominated Sorting Genetic Algorithm-II (NSGA-II)) approach is proposed to optimize the parameters of the LFM pulse train to achieve reduced grating lobes, low peak sidelobe level and narrow mainlobe width. The optimization problem has been studied in two different ways: first one is associated with the reduction of grating lobes and the minimization of peak sidelobe level of the ACF with constraints and second one is related to the minimization of the peak sidelobe level and mainlobe width of the ACF with constraints. Simulation studies have been carried out to justify the potentiality of the proposed approach.     

Observation of aphelion cloud belt over Martian tropics,its evolution,and associated dust distribution from MCS data

The present study uses five Martian years of observations from Mars Climate Sounder onboard Mars Reconnaissance Orbiter for investigating the Aphelion Cloud Belt (ACB) over the tropics. Analysis of zonal mean water ice column opacity suggests that the spatial extension of the ACB is mainly confined over the tropics and mid-latitudes (-20 – 40°N) during L_S ~ 45 – 135° (L_S = 0° signifies northern spring equinox). The ACB is seen primarily in the nighttime only due to the truncation of the daytime profile observations at significantly higher altitudes (at ~30 km). Zonal mean ice extinction profiles show ACB’s altitudinal range within ~10 – 40 km, and the existence of a thin cloud band in the absence of a thick ACB during aphelion season. Three phases of the ACB could be identified as the formation phase during L_S = 45 – 75° (phase 1), the peak phase during L_S = 76 – 105° (phase 2), and the decaying phase during L_S = 106 – 135° (phase 3). Observation of the cloud latitude belt shows a northward movement starting from phase 2, prominent over regions nearby Lunae Planum and Xanthe Terra. During this phase, the top level of thick clouds within the ACB decreases to ~20 km in the southern hemisphere, while it increases a little over the northern hemisphere (NH). The decreasing tendency continues in phase 3 over the entire region ?10 – 10°N, and the thick cloud base moves higher over the NH, though the vertical depth of it becomes narrower than phase 2. Temperature profiles do not show any noticeable influence on the northward evolution of the ACB. However, the study at a regional level indicates a possible association of upper tropospheric dustiness with the ACB’s evolution. The mechanism is evident in the correlation analysis mostly at an altitude range of ~18 – 35 km. The migrating semidiurnal tide (SMD) as a proxy of dust or water ice forcing, and the calculated upper tropospheric dust radiative heating, shows an apparent northward movement of their peak amplitude within the three phases of the ACB. This match between the spatiotemporal variations of the SMD and the water ice was not observed previously. However, the correlating behavior seems to be prominent in the areas nearby Lunae Planum and Xanthe Terra and the upper-tropospheric region of the atmosphere.