Welcome to the Remote Senesing and Spatial! Modelling Research Group
© Hanna Meyer

About us

The Research Group of "Remote Sensing and Spatial Modelling" is part of the Institute of Landscape Ecology (ILOEK) [en] of the University of Münster (WWU) [en]. We study and teach the acquisition and analysis of spatio-temporal environmental dynamics in a board spectrum of landscape-ecological topics. We combine multi-scale remote sensing data with methods of spatial modelling in order to obtain continuous spatio-temporal information from limited ecological field samples.
The complexity of environmental systems requires the use of modelling strategies that take complex relationships into account. For this reason, we focus on the application of machine learning methods. In addition to their application for research questions in the context of landscape ecology, we also develop new modelling strategies for spatial and spatio-temporal data. Thus, the research group is at the interface between Geoinformatics and Landscape Ecology [en] und and has the aim to contribute to an increase in knowledge in ecosystem research via satellite data processing, modelling and simulation.

New publication in Nature Communications

The recent wave of published global maps of ecological variables has caused as much excitement as it has received criticism. In our new publication "Machine learning-based global maps of ecological variables and the challenge of assessing them", we look into the data and methods mostly used for creating these maps, and discuss whether the quality of predicted values can be assessed, globally and locally.

Meyer H, Pebesma E. 2022. ‘Machine learning-based global maps of ecological variables and the challenge of assessing them.’ Nature Communications 13.
Link to the paper

New publication in Methods in Ecology & Evolution

In a new publication "Nearest neighbour distance matching Leave-One-Out Cross-Validation for map validation" led by our former master student Carles Mila, we propose a new cross-validation method that considers the geographical prediction space of spatial prediction models to obtain better accuracy estimates.

Mila C, Mateu J, Pebesma E, Meyer H. 2022. ‘Nearest neighbour distance matching leave-one-out cross-validation for map validation.’ Methods in Ecology and Evolution n/a.
Link to the paper [en]

WingtraOne
© Jan Lehmann

Study project Amtsvenn - The UAS-field season 2022 has been successfully started

As part of the study project Amtsvenn the first UAS flight campaign was successfully conducted on the 3rd of March 2022. High-resolution multispectral and very high-resolution RGB imagery was collected with the WingtraOne. The campaign was supervised by the “Biologische Station Zwillbrock e.V.” to survey the low disturbance of the UAS on wildlife and no disturbances were observed.
The study project investigates how UAS imagery can be used to detect and spatially model the humidity and vitality of bog vegetation. For ground truth, humidity and temperature are measured in a measurement setup developed by the students, representing different gradients (elevation, vegetation, degradation) of the bog.
This study projects follows the ongoing research in the Vechta bogs and kicks off the in April 2022 starting “Reversal Project” [en].
There are many research project, bachelor and master thesis topics for students interested in remote sensing and spatial modelling in bog ecosystems. If interested, please contact Jan Lehmann [en], Hanna Meyer [en] and Laura Giese [en].

Fieldwork in the snowy Fichtelgebirge

Measurements in the Carbon4D project are in full swing and will continue until the end of 2022. Every week, the team from the University of Bayreuth takes 3 cores in the study area to quantify the mineralization of soil organic carbon. Each month, the team from the University of Münster relocates all profile probes to measure soil temperature and moisture. In the picture gallery you can see some impressions of the field work in the snowy Fichtelgebirge. More information can be found on the project page [en].

Photos

Installation of a profile probe for measuring soil temperature and soil moisture.
Installation of a profile probe for measuring soil temperature and soil moisture.
© Maiken Baumberger
  • Drilling a hole for the installation of a profile probe.
    © Maiken Baumberger
  • Drilling a hole for a profile probe.
    © Linda Adorf
  • Taking a drill core to quantify soil organic carbon mineralization.
    © Maiken Baumberger
  • Equipment for the installation of a profile probe.
    © Maiken Baumberger
  • Knocking down a soil sampling corer to determine the soil texture.
    © Maiken Baumberger
  • Measurement of soil respiration with a soil respiration chamber.
    © Maiken Baumberger
  • Profile probe for measuring soil temperature and soil moisture.
    © Maiken Baumberger
  • Profile probe for measuring soil temperature and soil moisture.
    © Maiken Baumberger
Graphical Abstract of the paper
© Maite Lezama Valdes

New Publication in the project Antarctic Science Platform

What to do when the spatial or temporal resolution of satellite data is insufficient for the research topic? Our study shows how the strengths of two satellite sensors in terms of spatial and temporal resolution can be combined in a data-driven approach. As a result, from 1999 on, we can generate Land Surface Temperature data with a subdaily temporal and 30m spatial resolution for the Antarctic Dry Valleys – a dataset that can be used for various research applications, such as species distribution modelling or to model further relevant environmental information.

Group picture Earth Observation Network Meeting 2021
© Earth Observation Network

First meeting of the Earth Observation Network in the Bavarian Forest

From October 18 to 22 we met together with colleagues from different research institutions for a first joint meeting of our "Earth Observation Network" in the Bavarian Forest. During "Walk&Talk", presentations and joint data acquisition in the field, we exchanged ideas and planned joint research and teaching activities in the field of remote sensing. More information and pictures can be found on the pages of the Earth Observation network [en].

Welcome back...
© Jan Lehmann

We welcome all students to the new winter semester (2021/22). Information about our courses can be found under the entry Teaching [en].
Please note: The master module starts at the 25.10.

Screenshot of the course recordning
© OpenGeoHub

New online course about the area of applicability

The OpenGeoHub Summer School took place Online from 1 to 3 September 2021. We gave a workshop on „Mapping the area of applicability of spatial prediction models“. All course material [en] as well as video recordings of the Lecture/Practical [en] session is available online. Further information about the scientific project can be found on our pages on Uebersat [en].

Group picture of the project Carbon-4D
© Maiken Baumberger

Start of the field campaign of the Carbon-4D project

The first project meeting of the Carbon-4D project took place between the 7th and 10th of September in the Fichtel Mountains. In cooperation with the soil ecology group of the University of Bayreuth, Maiken Baumberger and Hanna Meyer installed profile probes for soil temperature and moisture measurements. From now on, the 15 probes will be moved every three weeks to measure at several different sites. Furthermore, the University of Bayreuth performs chamber measurements and analyses soil cores. The measured data will be used for the development of a 4D model for the mineralization of soil organic carbon on a landscape scale.
 

Winner of the poster price

in the B.Sc. module "Introduction to remote sensing"

Photos

© Konstantin Engelmayer & Emilio Sanchez
  • Poster von Antonia Bilger und Lena Wild
    © Antonia Bilger und Lena Wild
  • Poster von Anna Koch & Lara Hummel
    © Anna Koch & Lara Hummel
  • Poster von Janna Krickau & Jan Steen
    © Janna Krickau & Jan Steen
  • Poster von Emma Hebbeler & Maj Zimmermann
    © Emma Hebbeler & Maj Zimmermann
  • Poster von Arwen Henrich & Amke Hinrichs
    © Arwen Henrich & Amke Hinrichs
Profile picture Maiken Baumberger
© Maiken Baumberger

Welcome to the working group, Maiken!

Maiken Baumberger [en] is our new team member from August on.
She will work within the Carbon4D [en] project on the landscape-scale mdoelling of soil respiration.
Welcome to the working group, we are looking forward to working with you!

Symposium on Statistical Approaches for analyzing Remote Sensing Imagery

A digital symposium on Statistical Approaches for analyzing Remote Sensing Imagery will be held on July 23, 2021.
Organisation: Edzer Pebesma (WWU), Roland Fried (TU Dortmund), Hanna Meyer (WWU)
Speakers: Anton Thielmann, Marius Appel, Ribana Roscher, Emanuel Büechi, Jana Gierse, Maite Lezama-Valdes, Marvin Ludwig

  More information and registration [en].

Drohne flight
© Jan Lehmann

Field campaign on bird sanctuary islands “Große Kirr” and “Barther Oie”

As part of a master thesis and a research project, Jan Lehmann and the students Candy Fahrenholz and Henning Schneidereit accomplished a field campaign in the national park “Western Pomerania Lagoon Area” from the 13th of June until the 17th of June. With special permits of the national park, which are needed because of strict flight and entry bans, and in close cooperation with the staff of the national park, the two bird sanctuary islands, including active breeding colonies, were mapped with the WingtraOne. A multispectral dataset with information of about 700 hectare was collected and the reaction of the birds towards the drone were observed. The campaign did work out exceedingly well and now we are looking forward to analyse the dataset in aspects of vegetation and structure as well as for the inventory of breeding birds.

More information about the project. [en]

© Hanna Meyer

New publication in Methods in Ecology and Evolution

Can our machine learning models make reliable spatial predictions or are we predicting into unknown space? Find out in our recent publication on assessing the area of applicability of spatial prediction models that just got published Methods in Ecology and Evolution:

More information about the project Uebersat [en].

Virtual team meeting
© AG Fernerkundung

Our team is growing

Our team is growing!

Eva Bendix Nielsen is a PhD student at the University of Canterbury in New Zealand and will be working with us for the next months as a visiting scientist in the project Antarctic Science Platform [en].
Marvin Ludwig [en] starts with us on 1 April as a research assistant in the project Uebersat [en], and will work on the development of methods for the transferability of AI models in remote sensing.

Welcome to the working group, we are looking forward to working with you!

More News...

Older news can be found in the archive [en] of the Remote Sensing and Spatial Modelling Research Group.