The browser you are using is not supported by this website. All versions of Internet Explorer are no longer supported, either by us or Microsoft (read more here:

Please use a modern browser to fully experience our website, such as the newest versions of Edge, Chrome, Firefox or Safari etc.

AI Assisted Radar Rainfall Algorithms for Advanced Engineering Decision Support Systems

Funding agency: Innovationskontor Syd. Duration: 2021-ongoing

This project is part of the LU innovation Exploratory Pre-Seed Programme 2020. Rainfall is vital for life on earth, yet capable of becoming a threat to humans by causing floods [1]. Increasingly frequent extreme events call for developing knowledge on areal rainfall at resolutions as fine as a transient local storm to promote climate resilient solutions to the socio-environmental challenges concerning stormwater. This project deals with the development of advanced radar and AI-assisted rainfall estimation algorithms for multi-disciplinary climate-adaptive decision support systems.

Recently installed compact high-tech X-band weather radars in Sweden [2] are unique instruments of providing rainfall data over grids of 500 meters on the ground by scanning weather at multiple vertical levels within a minute. However, current methods for radar rainfall estimation are not optimized for the new technology to handle some major error sources effectively.

The project validates a deep learning algorithm development for improved spatiotemporally complete data that keeps the initial product’s resolution. Also, innovative, interdisciplinary applications benefiting from the new data are introduced. X-band weather radars were used to prevent urban flooding in developed countries. New applications, e.g., in agriculture, forestry, and building areas, will increase the added value of an instrument with rather high initial price, making it worthwhile for developing countries as well. 

A broad reference group from Lund University, SMHI, Sweden Water Research, and water utilities of VA SYD and NSVA support the project.


  • A developed framework, and a pack of algorithms, and descriptive, visualized outputs to easily illustrate their superiority over existing frameworks and algorithms.
  • Identify a list of applications that could be a valuable benchmark for developing interdisciplinary decision-support systems, of course, with interrelated and synergetic aspects related to hydroclimatic variability at local scale.
  • Seek new funding, e.g., by LU-innovation or Vinnova, to develop a specific prototype of a decision-support system to take full advantage of the innovation as such data has never been available for many applications.


[1] Hosseini, SH. (2019). "Disastrous floods after prolonged droughts have challenged Iran". FUF‐Bladet.

[2] Hosseini SH, Hashemi H, Berndtsson R, South N, Aspegren H, Larsson R, Olsson J, Persson A, Olsson L. (2020). "Evaluation of a new X-band weather radar for operational use in south Sweden". Water Sci Technol. 2020. 81(8):1623-1635.

Research Team

Hasan Hosseini (Principal Investigator), Doctoral Student at CMES and the Divison of Water Resources Engineering (Department of Building and Environmental Technology, Lund University)

hasan [dot] hosseini [at] tvrl [dot] lth [dot] se

Hossein Hashemi, CMES Researcher and Associate Professor at the Division of Water Resources Engineering (Department of Building and Environmental Technology, Lund University) 

hossein [dot] hashemi [at] tvrl [dot] lth [dot] se

Ronny Berndtsson, CMES Deputy Director and Professor at the Division of Water Resources Engineering (Department of Building and Environmental Technology, Lund University) 

ronny [dot] berndtsson [at] tvrl [dot] lth [dot] se


Photo by Noah Silliman on Unsplash