Prediction of Soil Organic Carbon Content in Complex Vegetation Areas Based on CNN-LSTM Model

Zhaowei Dong, Liping Yao, Yilin Bao, Jiahua Zhang (), Fengmei Yao, Linyan Bai and Peixin Zheng
Additional contact information
Zhaowei Dong: The Key Laboratory of Earth Observation of Hainan Province, Hainan Aerospace Information Research Institute, Sanya 572000, China
Liping Yao: College of Earth and Planetary Sciences, University of Chinese Academy of Sciences, Beijing 100049, China
Yilin Bao: College of Earth and Planetary Sciences, University of Chinese Academy of Sciences, Beijing 100049, China
Jiahua Zhang: The Key Laboratory of Earth Observation of Hainan Province, Hainan Aerospace Information Research Institute, Sanya 572000, China
Fengmei Yao: College of Earth and Planetary Sciences, University of Chinese Academy of Sciences, Beijing 100049, China
Linyan Bai: The Key Laboratory of Earth Observation of Hainan Province, Hainan Aerospace Information Research Institute, Sanya 572000, China
Peixin Zheng: Meteorological Information Center of Shanxi, Taiyuan 030002, China

Land, 2024, vol. 13, issue 7, 1-19

Abstract: Synthesizing bare soil pictures in regions with complex vegetation is challenging, which hinders the accuracy of predicting soil organic carbon (SOC) in specific areas. An SOC prediction model was developed in this study by integrating the convolutional neural network and long and short-term memory network (CNN-LSTM) algorithms, taking into consideration soil-forming factors such as climate, vegetation, and topography in Hainan. Compared with common algorithmic models (random forest, CNN, LSTM), the SOC prediction model based on the CNN-LSTM algorithm achieved high accuracy (R 2 = 0.69, RMSE = 6.06 g kg −1 , RPIQ = 1.96). The model predicted that the SOC content ranged from 5.49 to 36.68 g kg −1 , with Hainan in the central and southern parts of the region with high SOC values and the surrounding areas with low SOC values, and that the SOC was roughly distributed as follows: high in the mountainous areas and low in the flat areas. Among the four models, CNN-LSTM outperformed LSTM, CNN, and random forest models in terms of R 2 accuracy by 11.3%, 23.2%, and 53.3%, respectively. The CNN-LSTM model demonstrates its applicability in predicting SOC content and shows great potential in complex areas where obtaining sample data is challenging and where SOC is influenced by multiple interacting factors. Furthermore, it shows significant potential for advancing the broader field of digital soil mapping.

Keywords: soil organic carbon; deep learning; convolutional neural network; short-term and long-term memory (search for similar items in EconPapers)
JEL-codes: Q15 Q2 Q24 Q28 Q5 R14 R52 (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2073-445X/13/7/915/pdf (application/pdf)
https://www.mdpi.com/2073-445X/13/7/915/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jlands:v:13:y:2024:i:7:p:915-:d:1420715

Access Statistics for this article

Land is currently edited by Ms. Carol Ma

More articles in Land from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().