Probabilistic prediction by means of the propagation of response variable uncertainty through a Monte Carlo approach in regression random forest: Application to soil moisture regionalization

Dega, Ségolène; Dietrich, Peter; Schrön, Martin; Paasche, Hendrik

doi:10.3389/fenvs.2023.1009191

Cited by 10 publications

(2 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…General and specific mathematical solutions for uncertainty quantification of regression problems exist, for example, Monte Carlo (MC) (JCGM, 2008) approaches or quantile random forest (Meinshausen, 2006), respectively, albeit they may not necessarily consider the same aspects of uncertainty and result in different uncertainty quantification (Dega et al., 2023). From their methodological side, such uncertainty quantification methods are well developed and their application appears straight forward.…”

Section: Introductionmentioning

confidence: 99%

Quantification of data‐related uncertainty of spatially dense soil moisture patterns on the small catchment scale estimated using unsupervised multiple regression

Paasche

Schröter

2023

Vadose Zone Journal

Self Cite

View full text Add to dashboard Cite

Multiple regression analysis is a valuable method to reduce information gaps in a sparse soil moisture data set by fusing its information content with those of densely mapped data sets. Regression analysis utilizing uncertain data results in an indeterminate regression model and indeterminate soil moisture predictions when applying the regression model. We employ an unsupervised multiple regression approaches, taking optimally located sparse soil moisture measurements directly as coefficients in a linear regression model. We propagate data uncertainties into our probabilistic soil moisture estimation results by embedding the regression in a Monte Carlo approach. The computed uncertainty defines the quantitative limit for information retrieval from the resultant ensemble of soil moisture maps. This raises doubts on the true presence of some prominent channel-like features of increased soil moisture that are clearly visible in a previously and deterministically derived soil moisture map ignoring the presence of data uncertainty. The approach followed in this work is computationally simple and could be applied routinely to databases of similar size. Insufficient uncertainty communication by the data provider became the biggest obstacle in our efforts and led us to the insight that the geoscientific community may need to revise their standards with regard to uncertainty communication related to measured and processed data.

show abstract

Section: Introductionmentioning

confidence: 99%

Quantification of data‐related uncertainty of spatially dense soil moisture patterns on the small catchment scale estimated using unsupervised multiple regression

Paasche

Schröter

2023

Vadose Zone Journal

Self Cite

View full text Add to dashboard Cite

show abstract

“…The requirement of such a demanding spatiotemporal calibration has hindered a full embracement of the CRN roving method as this procedure only is possible for small study areas and for areas that are easy to access (Jeong et al., 2021). Recently, studies on mobile CRN detection at heterogeneous landscapes were published (e.g., Altdorff et al., 2023; Dega et al., 2023), which makes it even more important that additional calibration procedures are developed to ensure that accurate SM estimates also can be obtained in areas with different landcover and soil types. The calibration and validation of large‐scale space‐borne SM are often conducted using point‐scale measurements.…”

Section: Introductionmentioning

confidence: 99%

Mapping spatiotemporal soil moisture in highly heterogeneous agricultural landscapes using mobile dual‐spectra cosmic‐ray neutron sensing

Andreasen,

Kragh,

Meyer

et al. 2023

Vadose Zone Journal

View full text Add to dashboard Cite

Accurate large‐scale soil moisture (SM) maps are crucial for catchment‐scale hydrological models used for water resource management and warning systems for droughts, floods, and wildfires. SM can be mapped by mobile cosmic‐ray neutron (CRN) systems of moderated detectors at homogeneous landscapes of similar soil and vegetation. In this study, we present a new approach for mobile CRN detection to perform to its full potential, where CRN measurements can also be converted to SM at heterogeneous landscapes. The approach is based solely on thermal and epithermal neutron datasets obtained from mobile dual‐spectra CRN detection, combined with theoretical developments using a particle transport model. For each measurement point, the land cover type is identified using the thermal‐to‐epithermal (T/E) ratio, and the relevant neutron‐count‐to‐soil‐moisture conversion function is estimated from CRN stations located at the main land cover types in the catchment. With this approach, the requirement of collecting 100+ soil samples for each point along the survey route is omitted. We use this T/E‐dependent approach to obtain SM maps from 12 CRN surveys and compare it with a simple approach where only the conversion function from the agricultural site is used. SM by the simple approach is comparable to the estimates of the agricultural stations of a capacitance sensor network, while the estimates of the T/E‐dependent approach also compare well with the heathland and forest stations. With accurate SM estimates for all landcover types, the average error is reduced from 0.089 to 0.038 when comparing CRN SM with space‐borne Soil Moisture Active Passive Mission estimates.

show abstract

Hydrology on Solid Grounds? Integration Is Key to Closing Knowledge Gaps Concerning Landscape Subsurface Water Storage Dynamics

Oswald,

Angermann,

Bogena

et al. 2024

Hydrological Processes

View full text Add to dashboard Cite

Individual approaches to observe water dynamics across our landscape, from the land surface to groundwater, are many though they individually only provide glimpses into the real world due to their specific space–time scales. Comprehensive integration across all available observations is still largely lacking, limiting both our ability to reduce scientific knowledge gaps, and to guide land and water management using the best available scientific evidence. We argue that a stronger focus on integration of observational products, while utilising machine learning and accounting for current perceptual understanding is urgently needed to overcome this limitation. Since Europe is warming faster than any other continent, central Europe is undergoing a dramatic hydroclimatic transition about which such integrated observations would provide timely and valuable insights. Here, we present potential and gaps of current and planned observational methods. We argue that hyperresolution (sub km) integrated estimates of landscape water dynamics are feasible, which could significantly improve our ability to simulate vadose zone and groundwater dynamics, ultimately closing gaps in our current perception of hydrological processes in a temperate region under strong influence from climate change. We close by arguing that an interdisciplinary effort of various scientific communities is needed to enable this advancement.

show abstract

Probabilistic prediction by means of the propagation of response variable uncertainty through a Monte Carlo approach in regression random forest: Application to soil moisture regionalization

Cited by 10 publications

References 50 publications

Quantification of data‐related uncertainty of spatially dense soil moisture patterns on the small catchment scale estimated using unsupervised multiple regression

Quantification of data‐related uncertainty of spatially dense soil moisture patterns on the small catchment scale estimated using unsupervised multiple regression

Mapping spatiotemporal soil moisture in highly heterogeneous agricultural landscapes using mobile dual‐spectra cosmic‐ray neutron sensing

Hydrology on Solid Grounds? Integration Is Key to Closing Knowledge Gaps Concerning Landscape Subsurface Water Storage Dynamics

Contact Info

Product

Resources

About