Dynamic Data-Driven Genetic Algorithm for forest fire spread prediction

Intraday stock price forecasting based on variational mode decomposition

“…Time series modeling and prediction is receiving a large attention in different applications; including flood monitoring [1], social network modeling [2], fire prediction [3,4], commodity price forecasting [5], stock market modeling [6], and financial risk evaluation [7]. In particular, stock price time series modeling and forecasting is a hot topic in quantitative finance since accurate prediction of stock price is crucial to financial risk evaluation and asset allocation.…”

Short-term fire front spread prediction using inverse modelling and airborne infrared images

“…Denham et al (2012) successfully applied genetic algorithms (GA) to find the wind configurations that best resemble observations to launch an improved forecast. A combination of weather and fuel calibration using fire perimeters has also been implemented using FARSITE (Finney 1998) and high-performance computing, showing great improvements and potential for long-term predictions (Wendt et al 2011;Artés et al 2014).…”

Front shape similarity measure for data-driven simulations of wildland fire spread based on state estimation: Application to the RxCADRE field-scale experiment

“…at scales ranging from tens of meters up to several kilometers), wildland fires are usually described as fronts that self-propagate normal to themselves into unburnt vegetation; the local speed of the propa-gating front is referred to as the rate of spread (ROS). Current operational fire spread simulators adopt this regional-scale perspective using Eulerian [1,2] or Lagrangian [3,4] A possible approach to overcome these limitations is data assimilation (DA) [1,[5][6][7][8][9][10]. DA offers a valuable framework to integrate fire sensor observations into a computer model, with the goal to find optimal estimates of the targets or "control variables" (e.g.…”