Technological change co-determines agri-environmental performance and farm structural transformation. Meaningful impact assessment of related policies can be derived from farm-level models that are rich in technology details and environmental indicators, integrated with agent-based models capturing dynamic farm interaction. However, such integration faces considerable challenges affecting model development, debugging and computational demands in application. Surrogate modelling using deep learning techniques can facilitate such integration for simulations with broad regional coverage. We develop surrogates of the farm model FarmDyn using different architectures of neural networks. Our specifically designed evaluation metrics allow practitioners to assess trade-offs among model fit, inference time and data requirements. All tested neural networks achieve a high fit but differ substantially in inference time. The Multilayer Perceptron shows almost top performance in all criteria but saves strongly on inference time compared to a Bi-directional Long Short Term Memory.

中文翻译：

---

使用深度学习对详细农场级模型进行代理建模

技术变革共同决定农业环境绩效和农场结构转型。相关政策的有意义的影响评估可以从富含技术细节和环境指标的农场级模型中得出，并与捕捉动态农场互动的基于主体的模型相结合。然而，这种集成面临着相当大的挑战，影响模型开发、调试和应用中的计算需求。使用深度学习技术的替代建模可以促进具有广泛区域覆盖范围的模拟的这种集成。我们使用不同的神经网络架构开发农场模型 FarmDyn 的代理。我们专门设计的评估指标允许从业者评估模型拟合、推理时间和数据要求之间的权衡。所有测试的神经网络都达到了很高的拟合度，但推理时间却存在很大差异。多层感知器在所有标准中都显示出几乎顶级的性能，但与双向长短期记忆相比，可以大大节省推理时间。