Research Article
Exploration of the Spatio-Temporal Evolution and Influencing Factors of Fragmentation of Cultivated Land in China
Wu Yaqing*
Issue:
Volume 10, Issue 5, October 2025
Pages:
103-119
Received:
13 August 2025
Accepted:
16 September 2025
Published:
25 September 2025
Abstract: From the perspective of food security, cultivated land fragmentation is a major constraint to agricultural modernization. Based on 1-km resolution land use data from 1995 to 2020 in China, this study builds a comprehensive evaluation system and applies a Geographically Weighted Random Forest (GW-RF) model with SHAP interpretation to explore spatial-temporal patterns and the nonlinear, multi-factor drivers of fragmentation. Key findings include: (1) Fragmentation first intensified then eased, with clear regional differences—engineering efforts reduced fragmentation in the southwest by up to 18.7%, while urbanization and lagging land transfer increased it in the Huang-Huai-Hai region; the Qinghai-Tibet Plateau showed a unique “expansion–fluctuation” pattern under ecological policies. (2) Slope and population density are dominant nonlinear drivers, with threshold effects observed for precipitation, temperature, and elevation. For example, fragmentation rises sharply with slopes of 0–3° or population densities over 125 persons/km². (3) Spatial heterogeneity reveals that natural drivers vary by region and can be reshaped by policy—e.g., rainfall effects reversed in the southwest due to terracing, elevation constraints offset by farmland projects in Huang-Huai-Hai, and ecological policies reduced the impact of population density by 35% on the Plateau. The model highlights key thresholds (e.g., 800 mm rainfall, 3° slope) that support the need for region-specific governance.
Abstract: From the perspective of food security, cultivated land fragmentation is a major constraint to agricultural modernization. Based on 1-km resolution land use data from 1995 to 2020 in China, this study builds a comprehensive evaluation system and applies a Geographically Weighted Random Forest (GW-RF) model with SHAP interpretation to explore spatial...
Show More
Research Article
A Study on a Salt Solution Concentration Prediction Method Based on CNN-LSTM-Attention
Ziyang Pei,
Jianfeng Zhao,
Ningfeng Wang*
Issue:
Volume 10, Issue 5, October 2025
Pages:
120-128
Received:
1 September 2025
Accepted:
17 September 2025
Published:
25 September 2025
Abstract: The rapid and accurate analysis of ion concentrations in mixed salt solutions is a critical aspect of utilizing salt lake chemical resources. To explore an efficient and non-destructive detection method, this study proposes a deep learning model that fuses a Convolutional Neural Network (CNN), a Long Short-Term Memory (LSTM) network, and an Attention mechanism for the prediction of salt solution concentrations using Near-Infrared Spectroscopy (NIRS). First, single-component and two-component mixed salt solution samples of NaCl, KCl, and MgCl2 were prepared, and their near-infrared spectral data were collected. After applying Savitzky-Golay smoothing and derivative preprocessing to the spectra, a CNN-LSTM-Attention prediction model was constructed. A comparative analysis was conducted against common models such as Partial Least Squares Regression (PLSR), Support Vector Regression (SVR), and Random Forest (RF), and an ablation study was performed to analyze the contribution of each deep learning module. The results show that for single-component salt solutions, the proposed model's performance is comparable to that of the high-performing SVR and RF models. In complex mixed solutions with severe spectral overlap, the CNN-LSTM-Attention model demonstrated significant superiority, with its prediction accuracy surpassing all traditional baseline models across all mixed datasets, achieving a coefficient of determination (R2) as high as 0.973. The study concludes that the proposed CNN-LSTM-Attention model can effectively address the challenge of spectral overlap, demonstrating the potential of using deep learning for the quantitative analysis of complex mixture systems via near-infrared spectroscopy.
Abstract: The rapid and accurate analysis of ion concentrations in mixed salt solutions is a critical aspect of utilizing salt lake chemical resources. To explore an efficient and non-destructive detection method, this study proposes a deep learning model that fuses a Convolutional Neural Network (CNN), a Long Short-Term Memory (LSTM) network, and an Attenti...
Show More
