Ct-Hiffnet: A Contour-Texture Hierarchical Feature Fusion Network for Cropland Field Parcel Extraction from High-Resolution Remote Sensing Images DOI
Hao Wu,

Junyang Xie,

Weihao Deng

и другие.

Опубликована: Янв. 1, 2024

Язык: Английский

Spatial-temporal patterns of cultivated land expansion and intensification in Africa from 2000 to 2020 DOI Creative Commons
Mengxi Wang, Cong Wang, Qiong Hu

и другие.

International Journal of Agricultural Sustainability, Год журнала: 2025, Номер 23(1)

Опубликована: Март 12, 2025

Язык: Английский

Процитировано

0

Big Data-Driven Dynamic Analysis of Tourist Behavioral Trajectories and Intelligent Service Strategies in Tourist Attractions DOI Open Access

Guo Qiang Hu

Applied Mathematics and Nonlinear Sciences, Год журнала: 2025, Номер 10(1)

Опубликована: Янв. 1, 2025

Abstract This paper takes the behavioral trajectory dynamics of tourists in tourist attractions as research object on premise big data and adopts mean filtering technology to preprocess tourists’ trajectories. After that, LSTM RNN are used analyze preferences long-term short-term explore spatio-temporal factors affecting Finally, vector embedding hierarchical attention mechanisms applied recommend intelligent services for points interest. The results show that culling influencing reduces model’s recommendation performance affects decision visit MALS model has best effect at TOP = 10. In this paper, clustered into three categories: category one (52%): spending, cognition, education lower end scale, family trips main focus, food is extremely preferred. Category 2 (21%): higher education, mostly traveling with friends or alone, preferring humanities history, entertainment activities, catering food, scenic services. third group (27%): mainly undergraduates aged 18-25, couples, expenses, tour guide natural landscapes.

Язык: Английский

Процитировано

0

Fine extraction of multi-crop planting area based on deep learning with Sentinel- 2 time-series data DOI

Jingmin Jiang,

Jiahua Zhang, Xue Wang

и другие.

Environmental Science and Pollution Research, Год журнала: 2025, Номер unknown

Опубликована: Апрель 21, 2025

Язык: Английский

Процитировано

0

Cascade Learning Early Classification: A Novel Cascade Learning Classification Framework for Early-Season Crop Classification DOI Creative Commons

Weiling Kong,

Xiaoqi Huang,

Jialin Liu

и другие.

Remote Sensing, Год журнала: 2025, Номер 17(10), С. 1783 - 1783

Опубликована: Май 20, 2025

Accurate early-season crop classification is critical for food security, agricultural applications and policymaking. However, when performed earlier, the available time-series data gradually become scarce. Existing methods mainly focus on enhancing model’s ability to extract features from limited address this challenge, but extracted phenological information remains insufficient. This study proposes a Cascade Learning Early Classification (CLEC) framework, which consists of two components: preprocessing cascade learning model. Data generates high-quality optical, radar thermodynamic in early stages growth. The model integrates prediction task task, are interconnected through mechanism. First, supplement more growing stage. Then, carried out. Meanwhile, mechanism used iteratively optimize results. To validate effectiveness CLEC, we conducted experiments soybean, corn rice Northeast China. experimental results show that CLEC significantly improves accuracy compared five state-of-the-art models Furthermore, under premise obtaining reliable results, advances earliest identifiable timing, moving flowing third true leaf stage soybean flooding sowing rice. Although timing unchanged, its improved. Overall, offers new ideas solving challenges.

Язык: Английский

Процитировано

0

Mapping Crop Types for Beekeepers Using Sentinel-2 Satellite Image Time Series: Five Essential Crops in the Pollination Services DOI Creative Commons
Navid Mahdizadeh Gharakhanlou, Liliana Pérez, Nico Coallier

и другие.

Remote Sensing, Год журнала: 2024, Номер 16(22), С. 4225 - 4225

Опубликована: Ноя. 13, 2024

Driven by the widespread adoption of deep learning (DL) in crop mapping with satellite image time series (SITS), this study was motivated recent success temporal attention-based approaches mapping. To meet needs beekeepers, aimed to develop DL-based classification models for five essential crops pollination services Quebec province, Canada, using Sentinel-2 SITS. Due challenging task SITS, employed three models, namely one-dimensional convolutional neural networks (CNNs) (1DTempCNNs), spectral CNNs (1DSpecCNNs), and long short-term memory (LSTM). Accordingly, capture expert-free features, specifically targeting features 1DTempCNN LSTM 1DSpecCNN model. Our findings indicated that model (macro-averaged recall 0.80, precision F1-score ROC 0.89) outperformed both 1DTempCNNs 0.73, 0.74, 0.85) 1DSpecCNNs 0.78, 0.77, 0.88) underscoring its effectiveness capturing highlighting suitability Furthermore, applying convolution (Conv1D) across domain demonstrated greater potential distinguishing land covers types than it domain. This contributes providing insights into capabilities limitations various

Язык: Английский

Процитировано

0

Ct-Hiffnet: A Contour-Texture Hierarchical Feature Fusion Network for Cropland Field Parcel Extraction from High-Resolution Remote Sensing Images DOI
Hao Wu,

Junyang Xie,

Weihao Deng

и другие.

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

0