Browsing by Author "Koolagudi, Shashidhar G"

Now showing 1 - 2 of 2

Long Range Prediction of Indian Summer Monsoon Rainfall Using Data Mining and Statistical Approaches
(National Institute of Technology Karnataka, Surathkal, 2018) H, Vathsala; Koolagudi, Shashidhar G
The Indian subcontinent is mainly dependent on South-West monsoon for her fresh water needs. The variability of South-West monsoon decides the state of the economy of this region. This rainfall in the Indian context is also known as Indian Summer Monsoon. From the literature available, it may be noted that people of India have been aware of the reversal of winds over the Arabian sea from the turn of Christian era as the important information regarding the wind regime was understood by the traders due to the movement of ships for trade across the Indian Ocean. Nevertheless, since ancient times, there has been a great demand for accurate forecasting of Indian Summer Monsoon Rainfall (ISMR). Predictors are the parameters that have high influence on rainfall patterns. In the past, several predictors have been proposed by hard-core meteorologists for ISMR prediction. However, over the times, the role of the predictors for ISMR prediction is drastically changing due to climate shift and new issues like; pollution, global warming etc. In this regard, a holistic approach is essential to use popularly available computing techniques to study the correlation between various existing predictors and to define a new set for efficient prediction. It is also true that compared to linear prediction techniques the use of recent approaches such as probabilistic and ensemble methods are expected to give improved performance. New approaches use inherent nonlinear relations among the data for better prediction. Using the techniques like fuzzy logic, a new scenario may be defined in prediction, where prediction value can be more precise and quantitative than conventional range prediction. In the present work the ISMR data provided by reputed data acquisition agencies like; National Centers for Environmental Prediction - National Center for Atmospheric Research (NCEP-NCAR), India Meteorological Department (IMD) and Indian Institute of Tropical Meteorology (IITM); over a period of 37 years (1969-2005), have been used to predict the rainfall. Data mining approaches, like correlation analysis and association rule mining, are used to identify highly influential predictors. Sophisticated state-of-the-art classifiers such as Neural Networks, Neuro-Fuzzy systems are used to predict ISMR using highly influential predictors. An approach of fuzzy logic has been applied, to quantitatively predict rainfall in a small geographical area of South India. The proposed method is used to analyse the effect of South-Western and North-Eastern monsoons on the Indian peninsular region. The findings of the present research are observed to be highly efficient, compared to the existing traditional prediction approaches including the ones used by IMD; the official government organization responsible for ISMR prediction.
MINERAL IDENTIFICATION On MARTIAN SURFACE USING SUPERVISED LEARNING APPROACH FROM CRISM HYPERSPECTRAL DATA
(National Institute of Technology Karnataka, Surathkal, 2024) KUMARI, PRIYANKA; Shetty, Amba; Koolagudi, Shashidhar G
The availability of spectral libraries for CRISM (Compact Reconnaissance Imaging Spectrometer for Mars) data through NASA’s Planetary Data System has revolutionized the study of the surface mineralogy of Mars. However, building supervised learning models for mineral mapping remains a challenge due to the scarcity of ground-truth training data. In this thesis, an innovative framework is presented that leverages supervised learning to classify spectra within CRISM hyperspectral images. To overcome the data limitation, an augmentation approach is employed that creates the training data by augmenting the minerals available in the MICA spectral library, preserving key absorption signatures of each mineral class while introducing adequate variability. The framework includes a comprehensive pre-processing pipeline, featuring a novel feature extraction method to capture distinctive absorption patterns in the spectra. The approach is validated using CRISM images from diverse Martian locations and interactive mineral maps are also provided for the detected dominant minerals. While this initial framework ensures acceptable accuracy, utilizing more sophisticated learning models and advanced preprocessing techniques can enhance the performance of the framework. Spectra in remotely sensed hyperspectral images are often affected by the presence of continuum, which changes the global curvature of the spectra, although the key absorption signatures are present. The continuum removal process, one of the critical preprocessing steps in the pipeline, is modified from the traditional approach to a novel method named Segmented Curve Fitting, which can identify more absorption shoulder points in a spectrum and thus can detect the absorption features in it more distinctively. Lastly, the thesis introduces MICAnet, a specialized Deep Convolutional Neural Network (DCNN) architecture tailored for mineral identification using CRISM hyperspectral data. Inspired by Inception-V3 and InceptionResnet-V1 architectures, MICAnet leverages 1-dimensional convolutions for processing spectra at the pixel level. This innovative architecture represents a significant contribution, being the first solely dedicated to this objective. The performance of the mineral mapping framework is assessed using both simulated data of varying complexity and a real CRISM TRDR/MTRDR hyperspectral dataset. In conclusion, this study advances the field of planetary science and remote sensing by providing automated approaches for mineral identification and mapping on Mars, also, enhances the understanding of Martian surface mineralogy, offering valuable insights into the planet’s geological history and habitability.