Statistics - [PHD140] VENEZIA (182047): Ricevimento
Statistics - [PHD140] VENEZIA (182047): Spazio Moodle del corso (Moodle space for learning)
Pubblicato il 22/09/2020
Lo spazio Moodle del corso è aperto qui. Invito tutti i gli studenti a iscriversi nello spazio Moodle prima del corso (non c'è password, serve @unive.it oppure @stud.unive.it) - chi non sarà in presenza potrà accedere al link Zoom per seguire la classe da remoto. Se ci sono dubbi fatemi sapere.
The course material is uploaded on Moodle here. All students can register for the course (PHD 140, no password required to enrol in the course. But requires @unive.it or @stud.unive.it email id). For those you cannot the lessons in person, you can follow the lecture live on Zoom (link for each lecture on Moodle). All lessons will also be recorded. Feel free to contact me if you have any doubts.
Pubblicato il 22/09/2020
I am available to co-supervise students interested in the following topics for their Masters/PhD dissertation. Note: A main tutor either from Department of Economics or Department of Environmental Sciences, Informatics and Statistics will be required to be arranged by the student (I can offer suggestions depending on the scope of research topic).
You can express your interest by sending an email to email@example.com.
Impacts of Climate Change and Variability on environment/sectors: Using big data from climate observations/models, robust statistical/econometric methods, modelling (e.g. using R, Matlab, Python etc), examine historical climate and sectoral data for potential evidence of climate impacts (including economic impacts). Using projected climate model data for future and other socio-economic indicators, estimate projections of sectoral impacts under global warming scenarios. Students with background on machine learning (ML) can also benefit as the size of datasets will make model calibration attractive (e.g. for cluster analysis, predictions etc.). Sectors of Interest: Agriculture, Health and Energy (other thoughts and suggestions from students are also welcome).
Preparation and application of climate extreme indices: Extremes in climate at various spatio-temporal scales can have detrimental effect on society. The research community is often restricted due to lack of robust extreme indicators. Current work includes preparation of global gridded time-series (past and future) of a large set of meteorological indices, with an aim to address the growing demands of the sectoral impacts community. See https://doi.org/10.1594/PANGAEA.898014 for example.
Students with background in numerical modelling, computational skills (e.g. R, Matlab, Python, Fortran, NCL) and a passion for handling big data will be most suitable for above topics. Prior knowledge of climate science, data formats (e.g. NetCDF, grib file formats) and machine learning will be beneficial but not necessary.