Abstract
Purpose
Although soil total phosphorus (TP) is a primary and essential large element reflecting the soil fertility in agricultural ecosystems, studies on model development of TP and its differences between wheat and paddy lands after a long cultivation history at a regional scale are still limited. Hence, a comparison model of TP with different learning methods and datasets were built, and the relationship between environmental factors and TP were discussed.
Methods
TP from a long cultivation of either wheat or paddy agriculture systems was investigated, and the regression between TP and climate parameters (air temperatures, precipitation, humidity, and atmospheric pressure) and latitude were analyzed. A comparison of model development with six learning methods, including one statistical learning method (linear) and five machine learning methods (support vector regression, decision tree, random forest, XGBoost, and LightGBM), and two datasets (0–20 and 0–170-cm soil layers) was made. The models were evaluated by the root mean squared error (RMSE), mean deviation (RMD), mean absolute error (MAE), and model effective (EF).
Results
The results showed that the TP content of the top soil layer in wheat lands (0.89 ± 0.01 g kg−1) was significantly higher than that of paddy lands (0.63 ± 0.01 g kg−1). The annual average precipitation, humidity, and air temperature had significant negative relationships with TP content, while the annual average atmospheric pressure and latitude had significant positive relationships with TP. Most machine learning methods showed better performances than that of a statistical learning method with the highest r2 of 0.82. The different datasets used for model development had no significant effect on model performances.
Conclusion
The average TP content of the top soil layer tends to be greater in wheat lands than that in paddy lands after a long cultivation. Other than the different statistical parameters (the average, maximum, and minimum values) of each climate parameter, comprehensive climate parameters including the annual, semiannual, quarterly, and monthly air temperature, precipitation, humidity, and atmospheric pressure should be considered for further model development. Although different datasets in variable soil depth had no significant effect on model performances, machine learning methods such as random forest, XGBoost, and LightGBM are recommended for better performance than a linear learning method for soil TP model development. It is recommended that a comparison of different machine learning methods will help build a stronger model in similar studies.
Similar content being viewed by others
References
Alewell C, Ringeval B, Ballabio C, Robinson DA, Panagos P, Borrelli P (2020) Global phosphorus shortage will be aggravated by soil erosion. Nat Commun 11:4546
Boutin KD, Mitsch WJ, Everham E, Bakshi BR, Zhang L (2021) An evaluation of corn production within a Wetlaculture™ system at Buckeye Lake, Ohio. Ecol Eng 171:106366
Cai M, Luo A, Zhang Y, Lin X, Ye J (2003) Abdsorption of phosphate by iron plaque on rice roots in relation to phosphate uptake by rice (Abstract in English). Chinese J Rice Sci 94–97
Cheng Y, Li P, Xu G, Li Z, Gao H, Zhao B, Wang T, Wang F, Cheng S (2018) Effects of soil erosion and land use on spatial distribution of soil total phosphorus in a small watershed on the Loess Plateau, China. Soil Tillage Res 184:142–152
Du L, Zhang X, Zheng Z, Li T, Wang Y, Huang H, Yu H, Ye D, Liu T (2020) Paddy soil nutrients and stoichiometric ratios as affected by anthropogenic activities during long-term tillage process in Chengdu Plain. J Soils Sediments 20:3835–3845
Environment CMoEa (2011) Soil-determination of total phosphorus by alkali fusion–Mo-Sb anti spectrophotometric method. China Ministry of Ecology and Environment, Beijing, pp 10P;A4
Gao X-S, Xiao Y, Deng L-J, Li Q-Q, Wang C-Q, Li B, Deng O-P, Zeng M (2019) Spatial variability of soil total nitrogen, phosphorus and potassium in Renshou County of Sichuan Basin, China. J Integr Agric 18:279–289
Harrison S, McAree C, Mulville W, Sullivan T (2019) The problem of agricultural ‘diffuse’ pollution: Getting to the point. Sci Total Environ 677:700–717
He X, Wang Y, Li T, He S, Zheng Z, Zhang X, Huang H, Yu H, Liu T, Lin C (2019) Phosphorus losses under heavy rain from the sloping farmlands in the purple hilly region of Southwestern China. J Soils Sediments 19:4005–4020
Heung B, Ho HC, Zhang J, Knudby A, Bulmer CE, Schmidt MG (2016) An overview and comparison of machine-learning techniques for classification purposes in digital soil mapping. Geoderma 265:62–77
Jiang B, Mitsch WJ (2020) Influence of hydrologic conditions on nutrient retention, and soil and plant development in a former central Ohio swamp: a wetlaculture mesocosm experiment. Ecol Eng 157:105969
Jiao Y, Du P (2016) Performance measures in evaluating machine learning based bioinformatics predictors for classifications. Quant Biol 4:320–330
Li G, Yang M, Zhang Y, Grace J, Lu C, Zeng Q, Jia Y, Liu Y, Lei J, Geng X, Wu C, Lei G, Chen Y (2020a) Comparison model learning methods for methane emission prediction of reservoirs on a regional field scale: Performance and adaptation of methods with different experimental datasets. Ecol Eng 157:105990
Li H, Liu J, Li G, Shen J, Bergström LFZ (2015) Past, present, and future use of phosphorus in Chinese agriculture and its influence on phosphorus losses. Ambio 44:274–285
Li Z, Zhang R, Liu C, Zhang R, Chen F, Liu Y (2020b) Phosphorus spatial distribution and pollution risk assessment in agricultural soil around the Danjiangkou reservoir, China. Sci Total Environ 699:134417
Ma W, Ma L, Li J, Wang F, Sisák I, Zhang F (2011) Phosphorus flows and use efficiencies in production and consumption of wheat, rice, and maize in China. Chemosphere 84:814–821
Mitsch W, Jørgensen SE (2004) Ecological engineering and ecosystem restoration
Moazenzadeh R, Mohammadi B (2019) Assessment of bio-inspired metaheuristic optimisation algorithms for estimating soil temperature. Geoderma 353:152–171
Nath CP, Hazra KK, Kumar N, Praharaj CS, Singh SS, Singh U, Singh NP (2019) Including grain legume in rice–wheat cropping system improves soil organic carbon pools over time. Ecol Eng 129:144–153
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V (2011) Scikit-learn: Machine learning in Python. JMLR 12:2825–2830
Peng Y, Zhao L, Hu Y, Wang G, Wang L, Liu Z (2019) Prediction of soil nutrient contents using visible and near-infrared reflectance spectroscopy. ISPRS Int J Geoinf 8:437
Shen Q, Wang Y, Wang X, Liu X, Zhang X, Zhang S (2019) Comparing interpolation methods to predict soil total phosphorus in the Mollisol area of Northeast China. Catena 174:59–72
Smith DR, Macrae ML, Kleinman PJA, Jarvie HP, King KW, Bryant RB (2019) The latitudes, attitudes, and platitudes of watershed phosphorus management in North America. J Environ Qual 48:1176–1190
Smith P et al (1997) A comparison of the performance of nine soil organic matter models using datasets from seven long-term experiments. Geoderma 81:153–225
Ulén B, Bechmann M, Fölster J, Jarvie HP, Tunney H (2007) Agriculture as a phosphorus source for eutrophication in the north-west European countries, Norway, Sweden, United Kingdom and Ireland: a review. J Environ Qual 23:5–15
Uribe N, Corzo G, Quintero M, van Griensven A, Solomatine D (2018) Impact of conservation tillage on nitrogen and phosphorus runoff losses in a potato crop system in Fuquene watershed. Colombia Agric Water Manag 209:62–72
Vrebos D, Jones A, Lugato E, O’Sullivan L, Schulte R, Staes J, Meire P (2021) Spatial evaluation and trade-off analysis of soil functions through Bayesian networks. Eur J Soil Sci 72:1575–1589
Wang W, Wang C, Sardans J, Min Q, Zeng C, Tong C, Peñuelas J (2015) Agricultural land use decouples soil nutrient cycles in a subtropical riparian wetland in China. Catena 133:171–178
Wang Y, Zhao X, Guo Z, Jia Z, Wang S, Ding K (2018) Response of soil microbes to a reduction in phosphorus fertilizer in rice-wheat rotation paddy soils with varying soil P levels. Soil Tillage Res 181:127–135
Willcock S, Martínez-López J, Hooftman DAP, Bagstad KJ, Balbi S, Marzo A, Prato C, Sciandrello S, Signorello G, Voigt B, Villa F, Bullock JM, Athanasiadis IN (2018) Machine learning for ecosystem services. Ecosyst Serv 33:165–174
Xie X, Wu T, Zhu M, Jiang G, Xu Y, Wang X, Pu L (2021) Comparison of random forest and multiple linear regression models for estimation of soil extracellular enzyme activities in agricultural reclaimed coastal saline land. Ecol Indic 120:106925
Zhang Q, Song Y, Wu Z, Yan X, Gunina A, Kuzyakov Y, Xiong Z (2020) Effects of six-year biochar amendment on soil aggregation, crop growth, and nitrogen and phosphorus use efficiencies in a rice-wheat rotation. J Clean Prod 242:118435
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
All of the authors have read and approved the paper, and it has not been published previously nor is it being considered by any other peer-reviewed journal.
Conflict of interest
The authors declare no competing interests.
Additional information
Responsible editor: Jun Zhou
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chen, Y., Jia, J., Wu, C. et al. Estimation on total phosphorus of agriculture soil in China: a new sight with comparison of model learning methods. J Soils Sediments 23, 998–1007 (2023). https://doi.org/10.1007/s11368-022-03374-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11368-022-03374-x