Sökning: "long range forecasting"

Visar resultat 1 - 5 av 18 uppsatser innehållade orden long range forecasting.

  1. 1. Seasonal Variability of Ice Nucleating Particles (INP) in Southern Sweden

    Master-uppsats, Göteborgs universitet / Institutionen för biologi och miljövetenskap

    Författare :Tamina Kabir; [2023-03-08]
    Nyckelord :;

    Sammanfattning : Cloud ice crystals are formed by ice-nucleating particles (INPs). The micro-physical properties of clouds, precipitation formation and the life cycle of clouds are strongly influenced by the presence or absence of ice. Therefore knowledge of atmospheric INP concentrations is crucial to improve weather forecasting and climate projections. LÄS MER

  3. 2. Anticipating Glacier Lake Outburst Floods (GLOFs): an impact-based forecasting framework for managing GLOF risks in Nepal.

    Master-uppsats, Lunds universitet/Avdelningen för Riskhantering och Samhällssäkerhet

    Författare :Grace Muir; [2023]
    Nyckelord :Anticipatory Action; Impact-based Forecasting; Glacier Lake Outburst Flood; Nepal; Risk-informed Early Action; Prediction; Disaster Risk Management; Science General;

    Sammanfattning : Glacier lake outburst floods (GLOFs) are an increasingly documented threat across the Himalayan region, wherein Nepal is situated. GLOFs involve a rapid discharge of water from a lake situated at the side, front, within, beneath, or on the surface of a glacier. LÄS MER

  4. 3. Prediction and Analysis of 5G beyond Radio Access Network

    Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

    Författare :Gaurav Singh; Shreyansh Singh; [2023]
    Nyckelord :- LSTM; RNN; AE-LSTM; Deep Learning; Machine Learning; network traffic flow; forecasting; quality-of-service.;

    Sammanfattning : Network traffic forecasting estimates future network traffic based on historical traffic observations. It has a wide range of applications, and substantial attention has been dedicated to this research area. LÄS MER

  5. 4. Volatility Forecasting with Artificial Neural Networks: Can we trust them?

    Master-uppsats, Stockholms universitet/Finansiering

    Författare :Carl Oscar Dannström; Axel Broang; [2022]
    Nyckelord :;

    Sammanfattning : This thesis investigates how two types of artificial neural network models (ANN), feedforwardneural networks (FNN) and long short-term memory (LSTM), used for realized volatility (RV) forecasting, perform during high and low volatility regimes in comparison to the heterogeneousautoregressive (HAR) model. This is done for 23 stocks, constituents of the Swedish index OMXS30, between the 8th of February 2010 and the 31st of January 2022 using ten exogenous and three endogenous input variables. LÄS MER

  7. 5. Forecasting Efficiency in Cryptocurrency Markets : A machine learning case study

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Erik Persson; [2022]
    Nyckelord :Cryptocurrencies; Financial time-series; Multi step-ahead forecasting; Machine Learning; Feature selection; Kryptovalutor; Finansiella tidsserier; Flerstegsprognoser; Maskininlärning; variabelselektion;

    Sammanfattning : Financial time-series are not uncommon to research in an academic context. This is possibly not only due to its challenging nature with high levels of noise and non-stationary data, but because of the endless possibilities of features and problem formulations it creates. LÄS MER