Predicting the Zinc Content in Rice from Farmland Using Machine Learning Models: Insights from Universal Geochemical Parameters
Source abstract
Abstract
Zinc (Zn) is an essential nutrient for the human body and is prone to deficiency. Supplementing Zn through zinc-enriched cereals is of great significance in addressing the widespread issue of zinc deficiency. However, there is no simple linear correlation between the soil zinc content and rice grain zinc content, which poses challenges for zoning zinc-enriched rice cultivation based on the soil Zn content. Therefore, accurately predicting the zinc content in rice grains is of great importance. To verify the robustness of the prediction model and expand its applicability, this study established a prediction model using 371 sets of previously collected and tested rice grain and root zone soil samples from the Pearl River Delta and Heyuan regions in Guangdong. The model was validated using the data from 65 sets of rice and root zone soil samples collected and analyzed in Zijin and Dongyuan counties, Heyuan, in 2023. The results show that zinc absorption by rice grains is controlled by multiple factors, primarily related to the soil S, P, CaO, Mn, TFe2O3, TOC, and SiO2/Al2O3 ratio. Both the artificial neural network model and random forest model demonstrated a good predictive performance across large regions. However, in the Heyuan region, the random forest model outperformed the artificial neural network model, with an R2 of 0.79 and an RMSE of 0.05 when the predicted data were compared against the measured BAFZn of the rice. This suggests that predicting the zinc content in rice grains based on the soil macro-elements (including oxides) and TOC is feasible, and, within certain regional boundaries, the prediction model is robust and widely applicable. This study provides valuable insights into the rational development of zinc-enriched rice in the Heyuan region and offers a useful reference for establishing prediction models of the beneficial element content in rice grains in areas with limited data.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Geochemistry and Geologic Mapping
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Earth Sciences and Resources, China University of Geosciences, Beijing 100083, China
Guangdong Institute of Geological Survey, Guangzhou 510080, China
Research Center of Geochemical Survey and Assessment on Land Quality, Institute of Geophysical and Geochemical Exploration, Chinese Academy of Geological Sciences, Langfang 065000, China
Key Laboratory of Geochemical Cycling of Carbon and Mercury in the Earth’s Critical Zone, Institute of Geophysical and Geochemical Exploration, Chinese Academy of Geological Sciences, Langfang 065000, China
Key Laboratory of Ecological Geochemistry, Ministry of Natural Resources, Beijing 100037, China
School of Science, China University of Geosciences, Beijing 100083, China
Funding
Geological Exploration and Urban Geological Survey Project of Guangdong Province, China · National Nonprofit Institute Research Grant of IGGE
References (59)
Show source-provided references
1. Zinc, Zinc Nanoparticles and Plants10.1016/j.jhazmat.2018.01.040 ↗
2. Characteristics of zinc absorption and distribution after silking in the different maize inbred lines
3. Zinc Deficiency in Low- and Middle-income Countries: Prevalence and Approaches for Mitigation10.1111/jhn.12791 ↗
4. Hymenophyllum javanicum Spreng: An Addition to the Pteridophytic Flora of Central India10.1007/s40011-016-0782-3 ↗
5. Prom-U-Thai, C., Rashid, A., Ram, H., Zou, C., Guilherme, L.R.G., Corguinha, A.P.B., Guo, S., Kaur, C., Naeem, A., and Yamuangmorn, S. (2020). Simultaneous Biofortification of Rice with Zinc, Iodine, Iron and Selenium Through Foliar Treatment of a Micronutrient Cocktail in Five Countries. Front. Plant Sci., 11.10.3389/fpls.2020.589835 ↗
6. Improve Anthocyanin and Zinc Concentration in Purple Rice by Nitrogen and Zinc Fertilizer Application10.1016/j.rsci.2022.07.004 ↗
7. Agronomic Biofortification of Cereals with Zinc: A Review10.1111/ejss.12437 ↗
8. Progress in Species and Bioavailability of Heavy Metals in Soil
9. Zinc Concentration Prediction in Rice Grain Using Back-Propagation Neural Network Based on Soil Properties and Safe Utilization of Paddy Soil: A Large-Scale Field Study in Guangxi, China10.1016/j.scitotenv.2021.149270 ↗
10. Prediction and Risk Assessment of Five Heavy Metals in Maize and Peanut: A Case Study of Guangxi, China10.1016/j.etap.2019.103199 ↗
11. Prediction of Cadmium Contents in Rice Grains from Quaternary Sediment-Distributed Farmland Using Field Investigations and Machine Learning10.1016/j.scitotenv.2023.165482 ↗
12. Modelling Bioaccumulation of Heavy Metals in Soil-Crop Ecosystems and Identifying Its Controlling Factors Using Machine Learning10.1016/j.envpol.2020.114308 ↗
13. Estimation of Heavy Metals Using Deep Neural Network with Visible and Infrared Spectroscopy of Soil10.1016/j.scitotenv.2020.140162 ↗
14. Use of Artificial Neural Network to Evaluate Cadmium Contamination in Farmland Soils in a Karst Area with Naturally High Background Values10.1016/j.envpol.2022.119234 ↗
15. Prediction Heavy Metals Accumulation Risk in Rice Using Machine Learning and Mapping Pollution Risk10.1016/j.jhazmat.2023.130879 ↗
16. Geochemical characteristics of zinc in soil and prediction of zinc content in maize and rice grains in Linshui County, Sichuan Province
17. Geochemical characteristics of zinc in soil and prediction of Zn-rich wheat cultivating areas in Weining Plain, Northwest China
18. Using Machine Learning to Predict Selenium and Cadmium Contents in Rice Grains from Black Shale-Distributed Farmland Area10.1016/j.scitotenv.2023.168802 ↗
19. (2014). Specification of Multi-Purpose Regional Geochemical Survey (1:250 000) (Standard No. DZ/T 0258-2014).
20. (2016). Specification of Land Quality Geochemical Assessment (Standard No. DZ/T 0295-2016).
21. (2016). National Food Safety Standard for Multi-Element Determination in Foods (Standard No. GB5009.268-2016).
22. (2016). Regional Geochemical Sample Analysis Methods (Standard No. DZ/T 0279-2016).
23. National Multi-Purpose Regional Geochemical Survey in China10.1016/j.gexplo.2013.06.002 ↗
24. Application of Cadmium Prediction Models for Rice and Maize in the Safe Utilization of Farmland Associated with Tin Mining in Hezhou, Guangxi, China10.1016/j.envpol.2021.117202 ↗
25. A Field Study to Estimate Heavy Metal Concentrations in a Soil-Rice System: Application of Graph Neural Networks10.1016/j.scitotenv.2022.155099 ↗
26. Artificial Neural Networks for Neuroscientists: A Primer10.1016/j.neuron.2020.09.005 ↗
27. Neural Networks and Deep Learning: A Brief Introduction10.1007/s00134-019-05537-w ↗
28. Estimating the Soil Respiration Under Different Land Uses Using Artificial Neural Network and Linear Regression Models10.1016/j.catena.2018.11.035 ↗
29. Application of BP—ANN Model in Evaluation of Soil Quality in the Arid Area, Northwest China10.1016/j.still.2020.104907 ↗
30. Machine Learning in Environmental Research: Common Pitfalls and Best Practices10.1021/acs.est.3c00026 ↗
31. Multiaxial Fatigue Life Prediction Method Based on the Back-Propagation Neural Network10.1016/j.ijfatigue.2022.107274 ↗
32. Prediction of Plant Uptake and Translocation of Engineered Metallic Nanoparticles by Machine Learning10.1021/acs.est.1c01603 ↗
33. Prediction of Heat Transfer Due to Presence of Copper–Water Nanofluid Using Resilient-Propagation Neural Network10.1016/j.ijthermalsci.2008.11.009 ↗
34. Spatial Prediction of Soil Water Retention in a Páramo Landscape: Methodological Insight into Machine Learning Using Random Forest10.1016/j.geoderma.2017.12.002 ↗
35. Root Zone Soil Moisture Estimation with Random Forest10.1016/j.jhydrol.2020.125840 ↗
36. Modeling Flood Susceptibility Using Data-Driven Approaches of Naïve Bayes Tree, Alternating Decision Tree, and Random Forest Methods10.1016/j.scitotenv.2019.134979 ↗
37. Spatial Prediction of Soil Surface Texture in a Semiarid Region Using Random Forest and Multiple Linear Regressions10.1016/j.catena.2016.01.001 ↗
38. The Application of Machine Learning Methods for Prediction of Metal Sorption onto Biochars10.1016/j.jhazmat.2019.06.004 ↗
39. Prediction of Lead (Pb) Adsorption on Attapulgite Clay Using the Feasibility of Data Intelligence Models10.1007/s11356-021-12836-7 ↗
40. Accurate Prediction of Soil Heavy Metal Pollution Using an Improved Machine Learning Method: A Case Study in the Pearl River Delta, China10.1021/acs.est.2c07561 ↗
41. Mapping Soil Organic Matter Contents at Field Level with Cubist, Random Forest and Kriging10.1016/j.geoderma.2019.02.019 ↗
42. (2018). Soil Environment Quality—Risk Control Standard for Soil Contamination of Agriculture Land. Standard No. GB 15618-2018.
43. Selection and Breeding of Plant Cultivars to Minimize Cadmium Accumulation10.1016/j.scitotenv.2007.10.038 ↗
44. Influence of Soil Properties on Zinc Solubility Dynamics Under Different Redox Conditions in Non–Calcareous Soils10.1016/S1002-0160(17)60299-6 ↗
45. Effect of Sulfur Fertilization on Productivity and Grain Zinc Yield of Rice Grown Under Low and Adequate Soil Zinc Applications10.1016/j.rsci.2023.07.003 ↗
46. Influence of Hydrological Regime on Pore Water Metal Concentrations in a Contaminated Sediment-Derived Soil10.1016/j.envpol.2006.10.004 ↗
47. Cadmium Solubility in Paddy Soils: Effects of Soil Oxidation, Metal Sulfides and Competitive Ions10.1016/j.scitotenv.2010.12.028 ↗
48. Effects of Heavy Metals on Organic Matter Decomposition in Inundated Soils: Microcosm Experiment and Field Examination10.1016/j.scitotenv.2020.138223 ↗
49. Soil Organic Matter Prevails over Heavy Metal Pollution and Vegetation as a Factor Shaping Soil Microbial Communities at Historical Zn–Pb Mining Sites10.1016/j.chemosphere.2019.124922 ↗
50. Nitrogen Addition Promotes the Transformation of Heavy Metal Speciation from Bioavailable to Organic Bound by Increasing the Turnover Time of Organic Matter: An Analysis on Soil Aggregate Level10.1016/j.envpol.2019.113170 ↗
51. Ruehlmann, J., Bönecke, E., and Meyer, S. (2021). Predicting the Lime Demand of Arable Soils from pH Value, Soil Texture and Soil Organic Matter Content. Agronomy, 11.10.3390/agronomy11040785 ↗
52. Characteristics and Genesis of Supergene Manganese Ores in Xialei, Guangxi
53. Tang, J. (2011). Enrichment Characteristics and Poison Research to Crops of Heavy Metals in Fe-Mn Nodules Soil in Karst Area of Guangxi Central. [Ph.D. Thesis, China University of Geosciences].
54. Study on Zn and Cd Colloid-affected Adsorption in Three Different Soils
55. Study of Cu and Zn adsorption on the clay and its main components in surficial sediments
56. Formation Characteristics of Soils Developed from Metamorphic Rocks in the Hilly and Mountain Areas of Southwest Zhejiang Province
57. Rose, T., Kretzschmar, T., Liu, L., Lancaster, G., and Wissuwa, M. (2016). Phosphorus Deficiency Alters Nutrient Accumulation Patterns and Grain Nutritional Quality in Rice. Agronomy, 6.10.3390/agronomy6040052 ↗
58. Overuse of Phosphorus Fertilizer Reduces the Grain and Flour Protein Contents and Zinc Bioavailability of Winter Wheat (Triticum aestivum L.)10.1021/acs.jafc.6b04778 ↗
59. Influence of phosphorus on rice (Oryza sativa L.) grain zinc bioavailability and its relation to inositol phosphate profiles concentration10.3724/SP.J.1006.2020.92032 ↗