1
|
Xian W, Liu H, Yang X, Huang X, Huang H, Li Y, Zeng Q, Tang X. An ensemble framework for farmland quality evaluation based on machine learning and physical models. THE SCIENCE OF THE TOTAL ENVIRONMENT 2024; 912:168914. [PMID: 38029986 DOI: 10.1016/j.scitotenv.2023.168914] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/03/2023] [Revised: 11/22/2023] [Accepted: 11/25/2023] [Indexed: 12/01/2023]
Abstract
Farmland quality (FQ) evaluation is crucial to curb agricultural land's "non-grain" behavior and promote ecological nitrogen trade-off in North China. However, a promising approach to obtain the verified spatial distribution of nitrogen emissions remains to be developed, making it difficult to achieve the precise FQ estimation. Facing this issue, we present a Machine Learning (ML) - Nitrogen Export Verification (NEV) ensemble framework for the precise evaluation of FQ, taking the Beijing-Tianjin-Hebei 200 km traffic zone (zone) as the case. This was done by employing physical models for the precisely spatial estimation of Nitrogen Export (NE) values and then using ML methods to compute the spatial distribution of FQ using the Farmland Quality Evaluation System (FQES) indicators. We found: (1) the ML - NEV framework showed promising results, as the relative error of the NEV method was lower than 5.25 %, and the Determination coefficient of the ML method in FQ evaluation was higher than 0.84; (2) the FQ results within the zone were mainly good-quality areas (~47.25 % and primarily concentrated in the southwest-northeast regions) with improvement significance, with Fractal Dimension, NE values, and unbalanced Irrigation or Drainage Capabilities serving as the primary driving factors. Our results would be helpful in offering decision support for improving FQ based on refined grids, benefiting to Agribusiness Revitalization Plans (i.e., safeguarding grain yield, activating agribusiness development, Etc.) in developing countries.
Collapse
Affiliation(s)
- Weixuan Xian
- College of Natural Resources and Environment, Joint Institute for Environment & Education, South China Agricultural University, Guangzhou 510642, PR China
| | - Hang Liu
- Shijiazhuang vocational college of city economy, Shijiazhuang 052165, PR China
| | - Xingjian Yang
- College of Natural Resources and Environment, Joint Institute for Environment & Education, South China Agricultural University, Guangzhou 510642, PR China
| | - Xi Huang
- College of Natural Resources and Environment, Joint Institute for Environment & Education, South China Agricultural University, Guangzhou 510642, PR China
| | - Huiming Huang
- School of Land Science and Space Planning, Hebei GEO University, Shijiazhuang 050031, PR China
| | - Yongtao Li
- College of Natural Resources and Environment, Joint Institute for Environment & Education, South China Agricultural University, Guangzhou 510642, PR China
| | - Qijing Zeng
- College of Natural Resources and Environment, Joint Institute for Environment & Education, South China Agricultural University, Guangzhou 510642, PR China
| | - Xianzhe Tang
- College of Natural Resources and Environment, Joint Institute for Environment & Education, South China Agricultural University, Guangzhou 510642, PR China.
| |
Collapse
|
2
|
Ren Y, Xia J, Zeng S, Song J, Tang X, Yang L, Lv P, Fan D. Identifying critical regions for nitrogen and phosphorus loss management in a large-scale complex basin: The Jialing River. ENVIRONMENTAL RESEARCH 2023:116359. [PMID: 37295585 DOI: 10.1016/j.envres.2023.116359] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/12/2023] [Revised: 05/30/2023] [Accepted: 06/07/2023] [Indexed: 06/12/2023]
Abstract
The determination of critical management areas for nitrogen (N) and phosphorus (P) losses in large-scale basins is critical to reduce costs and improve efficiency. In this study, the spatial and temporal characteristics of the N and P losses in the Jialing River from 2000 to 2019 were calculated based on the Soil and Water Assessment Tool (SWAT) model. The trends were analyzed using the Theil-Sen median analysis and Mann-Kendall test. The Getis-Ord Gi* was used to determine significant coldspot and hotspot regions to identify critical regions and priorities for regional management. The ranges of the annual average unit load losses for N and P in the Jialing River were 1.21-54.53 kg ha-1 and 0.05-1.35 kg ha-1, respectively. The interannual variations in both N and P losses showed decreasing trends, with change rates of 0.327 and 0.003 kg ha-1·a-1 and change magnitudes of 50.96% and 41.05%, respectively. N and P losses were highest in the summer and lowest in the winter. The coldspot regions for N loss were clustered northwest of the upstream Jialing River and north of Fujiang River. The coldspot regions for P loss were clustered in the central, western, and northern areas of the upstream Jialing River. The above regions were found to be not critical for management. The hotspot regions for N loss were clustered in the south of the upstream Jialing River, the central-western and southern areas of the Fujiang River, and the central area of the Qujiang River. The hotspot regions for P loss were clustered in the south-central area of the upstream Jialing River, the southern and northern areas of the middle and downstream Jialing River, the western and southern areas of the Fujiang River, and the southern area of the Qujiang River. The above regions were found to be critical for management. There was a significant difference between the high load area for N and the hotspot regions, while the high load region for P was consistent with the hotspot regions. The coldspot and hotspot regions for N would change locally in spring and winter, and the coldspot and hotspot regions for P would change locally in summer and winter, respectively. Therefore, managers should make specific adjustments in critical regions for different pollutants according to seasonal characteristics when developing management programs.
Collapse
Affiliation(s)
- Yuanxin Ren
- Shaanxi Key Laboratory of Earth Surface System and Environmental Carrying Capacity, College of Urban and Environmental Sciences, Northwest University, Xi'an, 710127, China; Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, 400714, China; Chongqing School, University of Chinese Academy of Sciences, Chongqing, 400714, China
| | - Jun Xia
- Shaanxi Key Laboratory of Earth Surface System and Environmental Carrying Capacity, College of Urban and Environmental Sciences, Northwest University, Xi'an, 710127, China; Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, 400714, China; Chongqing School, University of Chinese Academy of Sciences, Chongqing, 400714, China; State Key Laboratory of Water Resources and Hydropower Engineering Science, Wuhan University, Wuhan, 430072, China
| | - Sidong Zeng
- Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, 400714, China; Chongqing School, University of Chinese Academy of Sciences, Chongqing, 400714, China.
| | - Jinxi Song
- Shaanxi Key Laboratory of Earth Surface System and Environmental Carrying Capacity, College of Urban and Environmental Sciences, Northwest University, Xi'an, 710127, China
| | - Xiaoya Tang
- Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, 400714, China; Chongqing School, University of Chinese Academy of Sciences, Chongqing, 400714, China
| | - Linhan Yang
- Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, 400714, China; Chongqing School, University of Chinese Academy of Sciences, Chongqing, 400714, China
| | - Pingyu Lv
- Water-Environment Monitoring Center for the Upper Reach of Changjiang, Changjiang Water Resource Commission, Chongqing, 40021, China
| | - Di Fan
- Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, 400714, China; Chongqing School, University of Chinese Academy of Sciences, Chongqing, 400714, China
| |
Collapse
|
3
|
Jiang J, Wang Z, Lai C, Wu X, Chen X. Climate and landuse change enhance spatio-temporal variability of Dongjiang river flow and ammonia nitrogen. THE SCIENCE OF THE TOTAL ENVIRONMENT 2023; 867:161483. [PMID: 36634765 DOI: 10.1016/j.scitotenv.2023.161483] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/26/2022] [Revised: 01/04/2023] [Accepted: 01/05/2023] [Indexed: 06/17/2023]
Abstract
The adverse impacts of climate and landuse change are threatening the availability of water quantity and its quality, yet there are limited understandings in the response of water availability to changing environment at different spatio-temporal scales. Aimed at quantifying the individual and superimposed effects of climate and landuse change on streamflow and ammonia nitrogen (NH3-N) load in the Dongjiang River Basin (DRB), we dynamically simulated the historical (1981-2010) and future (2030-2070) variation of runoff depth and NH3-N load coupling multiple regional climate model and landuse data. The increase in runoff depth (avg. +233.9 mm) due to climate change was about 33 times greater than that caused by landuse change (avg. -7.2 mm). Especially in the downstream of DRB (Hong Kong, Shenzhen and Dongguan cities, etc.), the maximum rise of runoff depth under climate change was near twice compared with baseline period, indicating the dominant control of climate change on runoff. Also there existed higher coefficient of variation (Cv) value of runoff in the dry season of downstream DRB, contributing potential great fluctuation in runoff. Besides, the variation of NH3-N load was jointly influenced by climate and landuse change, revealing an offset or amplification effect. Moreover, the variability of NH3-N load (Cv value as the metric) increased from 2030, reached a maximum in 2050, following decreased to 2070. The spatial distribution of NH3-N load, in general, presented a downward trend and concentrated near the water body, while the monthly average NH3-N load showed distinct peaks in spring and late summer temporally. Overall, the results highlight the significance of investigating the water availability under changing environment and more adaptive strategies should be proposed for better basin water management.
Collapse
Affiliation(s)
- Jie Jiang
- School of Civil Engineering and Transportation, State Key Laboratory of Subtropical Building Science, South China University of Technology, Guangzhou 510641, China; Pazhou Lab, Guangzhou 510335, China
| | - Zhaoli Wang
- School of Civil Engineering and Transportation, State Key Laboratory of Subtropical Building Science, South China University of Technology, Guangzhou 510641, China; Pazhou Lab, Guangzhou 510335, China.
| | - Chengguang Lai
- School of Civil Engineering and Transportation, State Key Laboratory of Subtropical Building Science, South China University of Technology, Guangzhou 510641, China; Pazhou Lab, Guangzhou 510335, China
| | - Xushu Wu
- School of Civil Engineering and Transportation, State Key Laboratory of Subtropical Building Science, South China University of Technology, Guangzhou 510641, China
| | - Xiaohong Chen
- Center for Water Resource and Environment, Sun Yat-sen University, Guangzhou 510275, China
| |
Collapse
|
4
|
Fate of Soil Residual Fertilizer-15N as Affected by Different Drip Irrigation Regimes. WATER 2022. [DOI: 10.3390/w14152281] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Soil residual N is a potential factor threatening the environment, but it is also an N fertilizer resource. Few studies have evaluated the fate of soil residual N under agronomic practice. The objective of this study was to investigate the distribution of residual N and its possible influencing factors with different irrigation regimes. Under three N residual situations created by the previous season using the 15N labeled urea, we employed lettuce as the plant material and three lower limits of drip irrigation including 75% (DR1), 65% (DR2), and 55% (DR3) accounting for the field water capacity as experimental treatments. A furrow irrigation treatment (FI) with the same irrigation regime as DR2 was used as control. Results showed that 2.1–4.8% of the residual 15N from the previous season was absorbed by the succeeding lettuce, 78.0–84.4% was still remained in the 0–80 cm soil, and 10.9–20.0% was unaccounted for. After harvest of succeeding lettuces, the soil residual 15N mainly existed in the mineral form. Moreover, the lettuce reuse efficiency for15N was positively correlated with the total residual 15N amount (p < 0.01) and the mineral 15N amount (p < 0.01). The overall results indicated that an appropriate irrigation regime (DR2) was conducive to promoting absorption of residual N by succeeding crop.
Collapse
|
5
|
Agricultural Structures Management Based on Nonpoint Source Pollution Control in Typical Fuel Ethanol Raw Material Planting Area. SUSTAINABILITY 2022. [DOI: 10.3390/su14137995] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/27/2023]
Abstract
Increasing the promotion and application of biofuel ethanol has been a national strategy in China, which in turn has affected changes in the raw material planting structure. This study analyzed the effects of agricultural land-use changes on water quality in a typical maize fuel ethanol raw material planting area. The results revealed that an increase in cultivated land and construction land would also increase the load of TN (total nitrogen) and TP (total phosphorus), while an expansion in forest land would reduce the load. As for crop structures, maize might have a remarkable positive effect on TN and TP, while rice and soybean performed in no significant manner. Furthermore, scenarios under the carbon neutralization policy and water pollution control were carried out to forecast the nonpoint source pollutants based on the quantitative relations coefficients. It was proven that maize planting was not suitable for vigorous fuel ethanol development. Reducing maize area in the Hulan River Basin was beneficial to reducing nonpoint source pollution. However, the area of maize should not be less than 187 km2, otherwise, the food security of the population in the basin would be threatened. Under the change in fuel ethanol policy, this study could provide scientific support for local agriculture land-use management in realizing the carbon neutralization vision and set a good example for the development of the fuel ethanol industry in other maize planting countries.
Collapse
|
6
|
Cui G, Bai X, Wang P, Wang H, Wang S, Dong L. Mechanism of Response of Watershed Water Quality to Agriculture Land-Use Changes in a Typical Fuel Ethanol Raw Material Planting Area-A Case Study on Guangxi Province, China. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2022; 19:ijerph19116499. [PMID: 35682082 PMCID: PMC9180297 DOI: 10.3390/ijerph19116499] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/22/2022] [Revised: 05/24/2022] [Accepted: 05/25/2022] [Indexed: 02/04/2023]
Abstract
Speeding up the promotion and application of biofuel ethanol has been a national strategy in China, which in turn has affected changes in the raw material planting structure. This study analyzed the response mechanism of water quality to agriculture land-use changes in a cassava fuel ethanol raw material planting area. The results revealed that an increase in cultivated land and construction land would lead to a rise in the load of TN (total nitrogen) and TP (total phosphorus), while an expansion in forest land and grassland area would reduce the load. As for crop structures, corn would have a remarkable positive impact on TN and TP, while rice and cassava performed in an opposite manner. Furthermore, scenarios under the carbon neutralization policy were carried out to forecast the nonpoint source pollutants based on the quantitative relations coefficients. It was proven that cassava planting was suitable for vigorous fuel ethanol development, but the maximum increase area of cassava should be 126 km2 to ensure economic benefits. Under the change in fuel ethanol policy, this study could provide scientific support for local agriculture land-use management in realizing the carbon neutralization vision and also set a good example for the development of the cassava fuel ethanol industry in other cassava-planting countries.
Collapse
Affiliation(s)
- Guannan Cui
- School of Ecology and Environment, Beijing Technology and Business University, Beijing 100048, China; (G.C.); (X.B.); (H.W.); (S.W.)
- State Environmental Protection Key Laboratory of Food Chain Pollution Control, Beijing Technology and Business University, Beijing 100048, China
- Key Laboratory of Cleaner Production and Integrated Resource Utilization of China National Light Industry, Beijing Technology and Business University, Beijing 100048, China
| | - Xinyu Bai
- School of Ecology and Environment, Beijing Technology and Business University, Beijing 100048, China; (G.C.); (X.B.); (H.W.); (S.W.)
- State Environmental Protection Key Laboratory of Food Chain Pollution Control, Beijing Technology and Business University, Beijing 100048, China
- Key Laboratory of Cleaner Production and Integrated Resource Utilization of China National Light Industry, Beijing Technology and Business University, Beijing 100048, China
| | - Pengfei Wang
- National Engineering Laboratory for Lake Pollution Control and Ecological Restoration, State Environment Protection Key Laboratory for Lake Pollution Control, Chinese Research Academy of Environmental Sciences, Beijing 100012, China;
| | - Haitao Wang
- School of Ecology and Environment, Beijing Technology and Business University, Beijing 100048, China; (G.C.); (X.B.); (H.W.); (S.W.)
- State Environmental Protection Key Laboratory of Food Chain Pollution Control, Beijing Technology and Business University, Beijing 100048, China
- Key Laboratory of Cleaner Production and Integrated Resource Utilization of China National Light Industry, Beijing Technology and Business University, Beijing 100048, China
| | - Shiyu Wang
- School of Ecology and Environment, Beijing Technology and Business University, Beijing 100048, China; (G.C.); (X.B.); (H.W.); (S.W.)
- State Environmental Protection Key Laboratory of Food Chain Pollution Control, Beijing Technology and Business University, Beijing 100048, China
- Key Laboratory of Cleaner Production and Integrated Resource Utilization of China National Light Industry, Beijing Technology and Business University, Beijing 100048, China
| | - Liming Dong
- School of Ecology and Environment, Beijing Technology and Business University, Beijing 100048, China; (G.C.); (X.B.); (H.W.); (S.W.)
- State Environmental Protection Key Laboratory of Food Chain Pollution Control, Beijing Technology and Business University, Beijing 100048, China
- Key Laboratory of Cleaner Production and Integrated Resource Utilization of China National Light Industry, Beijing Technology and Business University, Beijing 100048, China
- Correspondence:
| |
Collapse
|