Error correction of predictions from a simulation model using Random Forests

Reducing errors in predictions from forward simulation models is often achieved by model calibration or data assimilation. In our recently published manuscript, Youchen Shen and our team explore an alternative that involves correction of predictions using a machine learning algorithm (Random Forests). We use streamflow predictions from the global water balance model PCRGLOB-WB as case study. It is hypothesized that the forcings (e.g. precipitation) as well as the simulated state variables (e.g. streamflow) of the simulation are informative for the magnitude of the error in streamflow predicted by the model. In particular the use of the simulated state variables is an innovative aspect of our study.

The figure below compares the different scenarios (Basel (Rhine); NSE and KGE, larger values indicate smaller errors). Black-outlined boxes give the performance of the simulation model without error correction, for the calibrated and the uncalibrated simulation model. The coloured bars give the performance after error correction. Using only meteorogical driving variables in error correction (red bars) considerably reduces error. The use of simulated state variables (green, blue) further reduces errors.


The figure below shows the effect on the predicted hydrographs (black, observed streamflow; blue calibrated simulation model; red after error correction).


Our approach is promising as it shows that error correction using a random forest provides errors in streamflow predictions that are considerably smaller than those from a calibrated model. We also show that simulated model state is informative of the magnitude of the error. Read the full paper at

EGU General Assembly 2021

Like almost every year, we present our work at the EGU General Assembly, 19-30 April 2021. It is an online event. Our presentations are:

EGU21-7154 | vPICO presentations | HS2.5.1
Global scale hydrological modelling at 100 m, 1 h resolution, in Python
Kor de Jong, Marc van Kreveld, Debabrata Panja, Oliver Schmitz, and Derek Karssenberg
Thu, 29 Apr, 09:19–09:21

EGU21-7081 | vPICO presentations | AS3.19
Nationwide estimation of personal exposure to air pollution using activity-based field-agent modelling
Oliver Schmitz, Meng Lu, Kees de Hoogh, Nicole Probst-Hensch, Ayoung Jeong, Benjamin Flückiger, Danielle Vienneau, Gerard Hoek, Kalliopi Kyriakou, Roel C. H. Vermeulen, and Derek Karssenberg
Wed, 28 Apr, 11:34–11:36

EGU21-6355 | vPICO presentations | AS3.19
Global, high-resolution statistical modelling of NO2
Meng Lu, Oliver Schmitz, Kees de Hoogh, Perry Hystad, Luke Knibbs, Qin Kai, and Derek Karssenberg
Wed, 28 Apr, 11:06–11:08

EGU21-12504 | vPICO presentations | HS2.2.1
The nature and extent of bomb tritium remaining in deep soils
Jaivime Evaristo, Yanan Huang, Zhi Li, Kwok P. Chun, Edwin H. Sutanudjaja, and Marc F.P. Bierkens
Wed, 28 Apr, 13:52–13:57

EGU21-2340 | vPICO presentations | HS5.2.1
ULYSSES: a system for global multi-model hydrological seasonal predictions
Luis Samaniego, Stephan Thober, Matthias Kelbling, Robert Schweppe, Oldrich Rakovec, Pallav Shrestha, Alberto Martinez-de la Torre, Eleanor M. Blyth, Katie A. Smith, Gwyn Rees, Matthew Fry, Edwin Sutanudjaja, Niko Wanders, Marc FP Bierkens, and Rens van Beek
Thu, 29 Apr, 13:48–13:50

EGU21-2069 | vPICO presentations | GM6.9/HS13.30/NH1.24/NP8.2 | Highlight
The past and future dynamics of salt intrusion in the Mekong Delta
Sepehr Eslami, Maarten van der Vegt, Philip Minderhoud, Nam Nguyen Trung, Jannis Hoch, Edwin Sutanudjaja, Dung Do Doc, Tho Tran Quang, Hal Voepel, and Marie-Noëlle Woillez
Wed, 28 Apr, 15:55–15:57

EGU21-684 | vPICO presentations | HS2.5.1
A conceptual analytical framework to assess the large-scale effects of groundwater withdrawal on groundwater storage and surface water flow
Marc F.P. Bierkens, Edwin H. Sutanudjaja, and Niko Wanders
Thu, 29 Apr, 09:07–09:09

EGU21-125 | vPICO presentations | HS2.5.1
On the influence and limitations of hyper-resolution hydrological modelling – application of the 1 km PCR-GLOBWB model over Europe
Jannis Hoch, Edwin Sutanudjaja, Rens van Beek, and Marc Bierkens
Thu, 29 Apr, 09:05–09:07

A modelling paradigm for field-agent based modelling, hands-on workshop with open source software

Karssenberg1, D., Schmitz1, O., Verstegen2, J.A., de Jong1, K.

1Utrecht University, the Netherlands, 2University of Münster, Germany


We are organising this online workshop at the iEMSs Conference 2020,

Platform: ZOOM

The heterogeneous nature of environmental systems poses a challenge on researchers constructing environmental models. Many simulation models need to incorporate phenomena that are represented as spatially and temporally continuous fields as well as phenomena that are modelled as spatially and temporally bounded agents. Examples include mobile animals (agents) interacting with vegetation (fields) or water reservoirs (agents) as components of hydrological catchments (fields). We share ideas on the design and implementation of a new data model1,2 and modelling system for development of such field-agent based models. In addition, we present a short hands-on workshop with the software.


  1. de Bakker, M. P., de Jong, K., Schmitz, O. & Karssenberg, D. Design and demonstration of a data model to integrate agent-based and field-based modelling. Environ. Model. Softw. 89, 172–189 (2017).

  2. de Jong, K. & Karssenberg, D. A physical data model for spatio-temporal objects. Environ. Model. Softw. 122, 104553 (2019).

Tentative schedule

Important note: during the workshop we will demo the prototype software. If you wish, you can also run the examples that we will show yourself, during or after the workshop. For installation instructions and an explanation how to run the scripts, refer to

Workshop duration: 2 hours

  • Introduction to workshop (5 minutes)

  • Presentation and discussion on concepts and software for field-agent based modelling (workshop organizers) (30 minutes)

  • Demo / Hands-on workshop (workshop participants)

  • Discussion (all)

  • Wrap-up and next steps