NPTEL : NOC:Machine Learning for Earth System Sciences (Computer Science and Engineering)

Co-ordinators : Prof. Adway Mitra


Lecture 1 - Introduction

Lecture 2 - Basics of Spatio-Temporal Modeling

Lecture 3 - Geostatistical Equation for Spatio-Temporal Process

Lecture 4 - Gaussian Process Regression and Inverse Problems

Lecture 5 - Anomaly Event Detection

Lecture 6 - Extreme Events

Lecture 7 - Extreme Value Theory

Lecture 8 - Causality

Lecture 9 - Networks

Lecture 10 - Data Assimilation

Lecture 11 - Challenges and Opportunities for ML in ESS

Lecture 12 - Types of Machine Learning Problems in ESS

Lecture 13 - Convolutional Networks for Spatial Problems

Lecture 14 - Sequential Models for Temporal Problems

Lecture 15 - Probabilistic Models for Earth System Science

Lecture 16 - Identification of Indian Monsoon Predictors

Lecture 17 - Statistical Downscaling of Rainfall with Machine Learning

Lecture 18 - Detection of Anomaly and Extreme Events

Lecture 19 - Identifying Causal Relations from Time-Series - 1

Lecture 20 - Identifying Causal Relations from Time-Series - 2

Lecture 21 - Spatio-Temporal Modelling of Extremes

Lecture 22 - Hierarchical Bayesian Models for Spatio-Temporal Processes

Lecture 23 - Geostatistical modelling for mapping based on in-situ measurements

Lecture 24 - Nowcasting of Extreme Weather Events

Lecture 25 - Discovering Clustered Weather Patterns

Lecture 26 - Interpretable Machine Learning for Earth System Science

Lecture 27 - Object Detection in Satellite Imagery - 1

Lecture 28 - Object Detection in Satellite Imagery - 2

Lecture 29 - Image Fusion from Multiple Sources for Remote Sensing

Lecture 30 - Image Segmentation for Remote Sensing

Lecture 31 - Satellite Imagery as a Proxy for Geophysical Measurements

Lecture 32 - Precipitation Nowcasting from Remote Sensing

Lecture 33 - Deep Domain Adaptation for Remote Sensing

Lecture 34 - Introduction to Earth System Modelling

Lecture 35 - Stochastic Weather Generator

Lecture 36 - Physics-Inspired Machine Learning for Process Models - 1

Lecture 37 - Physics-Inspired Machine Learning for Process Models - 2

Lecture 38 - Parameterizations for Sub-Grid Processes Using ML

Lecture 39 - Data Assimilation for Earth System Model Correction

Lecture 40 - ML for Climate Change Projection and Course Conclusion