动态门增强的深度学习模型与多源远程传感协同作用,以优化小麦产量估计
Jian Li1,2, Junrui Kang1,2, Jian Lu2,3
1College of Information Technology, Jilin Agricultural University, Changchun, China.
Frontiers in plant science
|August 5, 2025
概括
一个新的专家空间时间融合混合 (STF-MoE) 模型使用遥感和环境数据准确估计小麦产量. 这种深度学习方法提供了可靠的收获前预测,改善了作物管理策略.
科学领域:
- 农业科学 农业科学
- 遥感 遥感 遥感 遥感
- 深度学习 (Deep Learning) 是一种深度学习.
背景情况:
- 准确的小麦产量估计对于全球粮食安全和有效的农业管理至关重要.
- 传统的方法经常与作物生长和环境因素的时空复杂性作斗争.
研究的目的:
- 引入和评估专家空间时间融合混合 (STF-MoE) 模型,以精确估计小麦产量.
- 为了提高预测准确性,利用多源遥感和环境数据.
主要方法:
- 开发了一个基于LSTM-Transformer的深度学习框架,STF-MoE.
- 整合了一个异质的专家组合 (MoE) 与一个自适应的门网.
- 合并的遥感数据 (NIRv,Fpar) 和环境变量 (相对湿度,DEM) 用于产量预测.
主要成果:
- 在最近的产量估计中获得了高精度 (R2 = 0.827,RMSE = 547.7 kg/ha).
- 在历史数据和极端气候事件中表现出强的性能,表现优于基线模型.
- 确定了相对湿度和DEM作为影响产量的关键因素,并启用了在收获前1-2个月的预估.
结论:
- STF-MoE模型通过动态门和专家专业化有效地解决了时空数据的复杂性.
- 该模型为预收割小麦产量估计提供了一个可扩展的解决方案,尽管极端产量地区存在挑战.
- 未来的研究将专注于优化计算效率和整合更高分辨率的数据.
相关概念视频
02:16Light Acquisition
8.6K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
8.6K
02:35Key Elements for Plant Nutrition
21.4K
Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the...
21.4K