A large number of applications that only a few years ago would have been considered impossible to be performed without any sort of human interaction are now autonomously executed by increasingly more powerful machines and sophisticated algorithms. Fed by an enormous quantity of available data, machine learning algorithms can learn, without being explicitly programmed, to solve complex tasks such as speech, face, and object recognition or to play and even defeat the best human players at the ancient game of Go.
Machine-learning is becoming an essential skill in many data-intensive scientific fields, including Geosciences. Datasets in Geosciences applications are growing in size and variety at an exceptionally fast rate, highlighting the need for new data processing and assimilation techniques that are able to exploit the information deriving from this data explosion. In this framework, Machine-learning techniques have the potential to push forward the state of the art of data processing techniques in geosciences.
This is an introductory-level course of Machine Learning. The aim of this course is to provide an overview of the main machine learning methods and their application to geophysical, geochemical, geological and environmental data.
The Summer School will be held on campus, in Pisa, at Dipartimento di Scienze della Terra, via Santa Maria, 53.
The program will be activated also in distance learning mode (TEAMS platform).
Aim
This course introduces students to the exciting world of machine learning (ML) with a specific focus on geosciences. By the end of this course, students will understand basic ML concepts and apply them to geoscience problems such as seismological data analysis, geochemical data analysis, climate modeling, and satellite images classification.
Learning Outcomes:
Understand key machine learning techniques (both supervised and unsupervised).
Apply ML techniques to geoscience datasets.
Develop critical thinking for model evaluation and optimization.
Introduction
Introduction to Machine Learning (ML)
Overview of machine learning and its relevance in geosciences.
Applications in geosciences: seismic interpretation, mineral exploration, and climate forecasting.
Brief on types of machine learning: supervised, unsupervised, and reinforcement learning.
Fundamental Concepts: Training, validation, and testing datasets. Overfitting and underfitting in models.
Hands-on: Explore a basic geoscience dataset (e.g., seismic data, temperature records, logs data) and understand the workflow for ML applications.
Optimization Techniques
Introduction to Optimization: Definition and relevance of optimization in machine learning models.
Optimization in geosciences: Finding best-fitting models for geological patterns.
Global and Local Optimization:
Local optimization: gradient descent, stochastic gradient descent.
Global optimization: simulated annealing, genetic algorithms.
Hands-on: Implement a gradient descent algorithm to fit a simple geoscience-related regression problem (e.g., predicting hydrological parameters from historical data).
Supervised Learning
Linear and Non-linear Regression:
Linear regression: fitting models to predict geological attributes (e.g., mineral concentrations).
Polynomial regression and decision trees for non-linear relationships.
Classification:
Logistic regression for binary classification tasks in geosciences (e.g., rock type classification).
K-Nearest Neighbors (KNN) and Support Vector Machines (SVM) for multiclass problems such as identifying land cover from satellite imagery.
Hands-on: Apply regression and classification techniques to real geoscience datasets. Predict and classify geological data (e.g. facies classification from well logs).
Unsupervised Learning
Clustering:
K-means clustering for geological feature discovery (e.g., identifying seismic clusters).
Hierarchical clustering and DB-Scan for deeper data segmentation (e.g. earthquake epicenter analysis).
Dimensionality Reduction: Principal Component Analysis (PCA) and Independent Component Analysis (ICA) for reducing complex geoscience data.
Hands-on: Use clustering to identify natural groups in seismic activity data. Perform PCA to reduce dimensions of images.
Deep Learning
Introduction to Neural Networks:
Basics of artificial neural networks (ANN) and their architecture.
Activation functions (ReLU, Sigmoid, etc.) and backpropagation.
Training and Optimization: Overfitting and regularization techniques (L1, L2). Optimizers: Adam, RMSProp, and learning rate scheduling.
Hands-on: Build a basic neural network for image classification.
Deep Learning for Geosciences
Convolutional Neural Networks (CNNs):
Understanding CNNs and their relevance in image-based geoscience data (e.g., satellite images, seismic waveforms).
CNN layers: convolution, pooling, fully connected layers.
Applications in Geosciences:
Satellite image analysis for land cover mapping.
Seismic image analysis for detecting geological structures.
Hands-on: Build a CNN to classify satellite images of different geological formations or map land cover changes.
Project: Machine Learning in Geosciences
In the last day, students will work on a small project where they apply the concepts learned throughout the course to a specific geoscience problem.
Who can apply
Graduate Students, Early-Stage Researchers, Professionals.
Language
English
Program Intensity
Full-time
Application
Admission Requirements
Being Graduate Students, Early-Stage Researchers, Professionals.
Basic knowledge of calculus, linear algebra and statistics.
Basic knowledge of Python Programming.
IMPORTANT NOTICE:
- The Summer School will be activated with at least 10 students
- The maximum number of participants is set to 30 students
- Eligible participants will be admitted following a first come first served rule with subsequent payment of the tuition fees.
- Applications may be closed ahead of the scheduled application deadline in case of early reaching of the maximum number of eligible students
Required Documents
- Identity Document (*PASSPORT in case you are a foreign student*)
- Enrolment Form
- Curriculum Vitae
All the documents must be in pdf format, in order to upload them on the portal when required.
Application has to be submitted via Alice portal following the instructions of the "How to apply" page.
ECTS
3
Fees
500 euro
Pay fees by Debit/Credit Card or PayPal online using the following form filling it with all the required data:
NOTICE:
- International students without Italian Tax Code: please tick the box 'Anonymous' in order to disable the field 'Italian personal ID/VAT number'.
- Please type your NAME and SURNAME next to the pre-filled text of the field 'Reason'
- Please pay only after receiving the admission letter
REFUND POLICY:
- By 1 May 2025 (included) tuition fees may be fully refunded.
- After 1 May 2025 there will be no refund of the paid tution fees.
Period
30 June - 4 July 2025
Application Deadline
1 May 2025
IMPORTANT NOTICE: Applications may be closed ahead of the scheduled application deadline in case of early reaching of the maximum number of eligible students
Contacts
Coordinator
Prof. Francesco Grigoli Questo indirizzo email è protetto dagli spambots. È necessario abilitare JavaScript per vederlo.
Summer/Winter School Office Questo indirizzo email è protetto dagli spambots. È necessario abilitare JavaScript per vederlo.