ORCID Profile
0000-0003-2764-0078
Current Organisation
Wageningen University
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Copernicus GmbH
Date: 04-03-2021
DOI: 10.5194/EGUSPHERE-EGU21-8279
Abstract: & & In this work we compare the performance of machine learning metamodels of different scale for the prediction of pasture grass nitrogen response rate using a case study across different locations in New Zealand. We first used a range of soil, plant and management parameters known to affect grass growth and/or nitrogen response. These generated a complete factorial that enabled us to run virtual nitrogen response rate experiments, using the APSIM simulation model, in eight locations around the country. We included 40 years of weather data to capture the effect of weather variability on response rate. This created a large database with which to train machine learning models. We created local, regional, and nation-wide models using Random Forest and tested them on known and unknown locations. To evaluate the models, we first calculated the RMSE, MAE and R& sup& & /sup& and then determined if the distributions of the predictions were statistically different using the Mann-Whitney U test. Finally, we explore the generalizability of the models using the error metrics and the results of the statistical test.& &
Publisher: Springer Netherlands
Date: 18-12-2010
Publisher: Elsevier BV
Date: 12-2010
Publisher: Springer Netherlands
Date: 18-12-2010
Publisher: Elsevier BV
Date: 07-2008
Publisher: Wageningen University and Research
Date: 27-03-2023
DOI: 10.18174/SESMO.18563
Abstract: Models of socio-environmental or social-ecological systems (SES) commonly address problems requiring interdisciplinary scientific expertise and input from a heterogeneous group of stakeholders. In SES modelling multiple interactions occur on different scales among various phenomena. These scale phenomena include the technical, such as system variables, process detail, inputs and outputs, which most often require spatial, temporal, thematic and organisational choices. From a good practice and project efficiency perspective, the problem scoping and conceptual model formulation phase of modelling is the one to address well from the outset. During this phase, intense and substantive discussions should arise regarding appropriate scales at which to represent the different phenomena. Although the details of these discussions influence the path of model development, they are seldom documented and as a result often forgotten. We draw upon personal experience with existing protocols and communications in recent literature to propose preliminary guidelines for documenting these early discussions about the scale(s) of the studied phenomena. Our guidelines aim to aid modelling group members in building and capturing the richness of their rationale for scoping and scale decisions. The resulting transcripts are intended to promote transparency of modelling decisions and provide essential support for the justification of the final model for its intended use. They also facilitate adaptive modifications of the pathway of model development via retracing decisions and iterative reflection upon alternative scale options.
Publisher: Elsevier BV
Date: 12-2011
Publisher: Elsevier BV
Date: 05-2013
Publisher: Copernicus GmbH
Date: 15-05-2023
DOI: 10.5194/EGUSPHERE-EGU23-2649
Abstract: A solid understanding of the global water cycle and how land surface processes respond to both changes in climate and pressure due to water use is essential for society. Although Land Surface Models (LSM) and Global Hydrological Models (GHM) are able to simulate the spatiotemporal variability of the water balance relatively reliably, intercomparison studies have indicated considerable differences between the models. Each LSM and GHM present a unique set of equations, parameters and configurations that contribute to the spread of simulated hydrological responses to meteorological forcings. In order to improve our understanding of modeling uncertainties, we propose a variable importance assessment for 5 LSM/GHM (JULES, HTESSEL, PCR-GLOBWB, SURFEX and ORCHIDEE) from the EartH2Observe (E2O) project. The output of the models and the meteorological forcings were collected from the Water Resources Reanalysis Tier 2 of the E2O project, which consists of a global dataset with spatial resolution of 0.25ox0.25o. We used soil texture and land cover datasets that most resemble the inputs used by each LSM/GHM during the E2O project. The models& #8217 outputs were used to estimate 6 hydrological indices for every land cell: Evaporation-Precipitation ratio Runoff-Precipitation ratio Surface Runoff-Total Runoff ratio median Soil Moisture variation caused by a Rainfall event median Surface Runoff caused by a Rainfall event and Soil Moisture temporal autocorrelation. Then, we evaluate the input features (meteorological, land cover, and soil texture) importance to the hydrological indices of each model using machine learning. With the analysis we aim to & examine a) How much the models differ and why? b) To what extent are the output differences related to the input features or/and to the models formulation? and c) How significant is each feature to the respective hydrological index?
Publisher: Elsevier BV
Date: 12-2009
Publisher: Springer International Publishing
Date: 2021
Publisher: Elsevier BV
Date: 10-2015
Publisher: Elsevier BV
Date: 10-2015
Publisher: Elsevier BV
Date: 05-2009
Publisher: Elsevier BV
Date: 10-2015
Publisher: Elsevier
Date: 2008
Publisher: Elsevier BV
Date: 05-2011
Publisher: Elsevier BV
Date: 07-2014
Publisher: Elsevier BV
Date: 02-2015
Publisher: Wiley
Date: 25-04-2020
DOI: 10.1111/NPH.16544
Location: Switzerland
No related grants have been discovered for Ioannis Athanasiadis.