Benefits of hierarchical predictions for digital soil mapping-An approach to map bimodal soil pH

被引:6
|
作者
Nussbaum, Madlene [1 ]
Zimmermann, Stephan [2 ]
Walthert, Lorenz [2 ]
Baltensweiler, Andri [2 ]
机构
[1] Bern Univ Appl Sci BFH, Sch Agr Forest & Food Sci HAFL, Langgasse 85, CH-3052 Zollikofen, Switzerland
[2] Swiss Fed Inst Forest Snow & Landscape Res WSL, Zurcherstr 111, CH-8903 Birmensdorf, Switzerland
关键词
Digital soil mapping; Hierarchical predictions; Bimodal response; Soil pH; Acidity buffer ranges; Prediction uncertainty; ORGANIC-CARBON; HIGH-RESOLUTION; GLOBALSOILMAP; SUPPORT;
D O I
10.1016/j.geoderma.2023.116579
中图分类号
S15 [土壤学];
学科分类号
0903 ; 090301 ;
摘要
Maps of soil pH are an important tool for making decisions in sustainable forest management. Accurate pH mapping, therefore, is crucial to support decisions by authorities or forest companies. Soil pH values typically exhibit a distinct distribution characterized by two frequently encountered pH ranges, wherein aluminium oxides (Al2O3) and carbonates (CaCO3) act as the primary buffer agents. Soil samples with moderately acid pH values (pH CaCl2 of 4.5-6) are less commonly observed due to their weaker buffering capacity. The different strength of buffer agents results in a distinct bimodal distribution of soil pH values with peaks at pH of around 4 and 7.5. Commonly used approaches for spatial mapping neglect this often observed characteristic of soil pH and predict unimodal distributions with too many moderately acid pH values. For ecological map applications this might result in misleading interpretations.This article presents a novel approach to produce pH maps that are able to reproduce pedogenic processes. The procedure is suitable for bimodal responses where the response distribution is naturally inherent and needs to be reproduced for the predictions. It is model-agnostic, namely independent from the used statistical prediction method. Calibration data is optimally split into two parts corresponding each to a data culmination, i.e. for soil pH values belonging to the ranges of the two principal buffer agents (Al2O3 and CaCO3). For each subset a separate model is then built. In addition, a binary model is fitted to assign every new prediction location a probability to belong either to Al2O3 or CaCO3 buffer range. Predictions are combined by weighted mean. Weights are derived from probabilities predicted by the binary model. Degree of smoothness is chosen by sigmoid transform which allows for optimal continuous transition of the pH values between Al2O3 and CaCO3 buffer ranges. For each location uncertainty distributions may be combined by using the same weights.We illustrated application of the new approach to a medium and strong bimodal distributed response (1) pH in 0-5 cm and (2) pH in 60-100 cm of forest soils in Switzerland (2530 calibration sites). While model performance measured at 354 validation sites slightly dropped compared to a common modelling approach (drop of R2 of 0.02-0.03) distributional properties of the predictions are much more meaningful from a pedogenic point of view. We were able to demonstrate the benefits of considering specific distributional properties of responses within the prediction process and expanded model assessment by comparing observed and predicted distributions.
引用
收藏
页数:11
相关论文
共 50 条
  • [1] Validation of uncertainty predictions in digital soil mapping
    Schmidinger, Jonas
    Heuvelink, Gerard B. M.
    GEODERMA, 2023, 437
  • [2] Updating a national soil classification with spectroscopic predictions and digital soil mapping
    Teng, Hongfen
    Rossel, Raphael A. Viscarra
    Shi, Zhou
    Behrens, Thorsten
    CATENA, 2018, 164 : 125 - 134
  • [3] Updating the national soil map of Nepal through digital soil mapping
    Lamichhane, Sushil
    Kumar, Lalit
    Adhikari, Kabindra
    GEODERMA, 2021, 394
  • [4] PRODUCTION OF A SOIL MAP ASOCIATING COMMON DIGITAL SOIL MAPPING TECHNIQUES WITH HAND DELINEATION OF SOIL MAPPING UNITS
    Teske, Rodrigo
    Giasson, Elvio
    Bagatini, Tatiane
    REVISTA BRASILEIRA DE CIENCIA DO SOLO, 2015, 39 (04): : 950 - 959
  • [5] Mapping soil digitally with object based image analysis to improve soil map inputs to Digital Soil Mapping
    Wilson, P.
    Gregory, L.
    Herklots, A.
    Starkey, A.
    GLOBALSOILMAP: BASIS OF THE GLOBAL SPATIAL SOIL INFORMATION SYSTEM, 2014, : 301 - 306
  • [6] Digital soil mapping of Italy to map derived soil profiles with neural networks
    Fantappie, Maria
    LAbate, Giovanni
    Schillaci, Calogero
    Costantini, Edoardo A. C.
    GEODERMA REGIONAL, 2023, 32
  • [7] Biplots for understanding machine learning predictions in digital soil mapping
    van der Westhuizen, Stephan
    Heuvelink, Gerard B. M.
    Gardner-Lubbe, Sugnet
    Clarke, Catherine E.
    ECOLOGICAL INFORMATICS, 2024, 84
  • [8] Creating a Soil Map Using Digital Soil Mapping on the Example of the Diurtiulinsky Municipal District
    Shafeeva, Elina
    Miftakhov, Ilnur
    Ishbulatov, Marat
    Lykasov, Oleg
    ASIAN JOURNAL OF WATER ENVIRONMENT AND POLLUTION, 2022, 19 (03) : 89 - 95
  • [9] Approaches to Modernization of the State Soil Map of Russia on the Basis of the Methods of Digital Soil Mapping
    Korolyuk, T. V.
    Ovechkin, S. V.
    EURASIAN SOIL SCIENCE, 2010, 43 (05) : 488 - 498
  • [10] Approaches to modernization of the state soil map of Russia on the basis of the methods of digital soil mapping
    T. V. Korolyuk
    S. V. Ovechkin
    Eurasian Soil Science, 2010, 43 : 488 - 498