发表机构
African School of Economics（非洲经济学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对小农户作物损害评估中漏检成本高问题，提出CascadeCropNet级联架构，通过阈值选择满足召回约束，经实验验证该架构能有效减少漏检，在可靠性优先场景下可实现安全导向决策约束。
AI 中文摘要
在针对小农户的基于图片的农业保险中，漏检损害的成本远高于误报：遭受实际损失的农民得不到赔付，而不必要的专家审查虽成本高但可挽回。标准多类分类器优化全局精度，但在推理时无法操作或控制这种不对称成本结构。我们提出CascadeCropNet，一种两阶段级联架构，通过阈值选择校准以满足目标召回约束（Rec-Damaged >= 0.95）。轻量级哨兵模型进行二元健康分类；超过校准损害概率阈值tau的样本被升级到专家模型进行细粒度诊断。该设计在不重新训练的情况下提供了对安全-效率权衡的明确部署时控制。在实地数据集上评估，级联在tau = 0.5时实现Rec-Damaged = 0.974，相对于平坦基线减少漏检损害情况达54%。结果表明级联架构可通过校准路由在可靠性比总体精度更重要的设置中实现面向安全的决策约束。
英文摘要
In picture-based agricultural insurance for smallholder farmers, missed damage detections carry substantially higher cost than false alarms: a farmer who sustained real losses receives no payout, while unnecessary expert review is operationally costly but reversible. Standard multi-class classifiers optimize global accuracy but provide no mechanism to operationalize or control this asymmetric cost structure at inference time. We propose CascadeCropNet, a two-stage cascade architecture calibrated to satisfy a target recall constraint (Rec-Damaged >= 0.95) through threshold selection. A lightweight Sentinel model performs binary health triage; samples exceeding a calibrated damage probability threshold tau are escalated to a specialist Expert model for fine-grained diagnosis. This design provides explicit, deployment-time control over the safety-efficiency trade-off without retraining. Evaluated on the Eyes on the Ground dataset (23,804 images from Kenyan smallholder maize farms), the cascade achieves Rec-Damaged = 0.974 at tau = 0.5, reducing missed damage cases by up to 54% relative to a flat baseline. Under evaluation alignment, the representational gap reduces to +0.008 F1-macro, confirming the contribution is architectural rather than representational. Under input degradation, the system prioritizes escalation over confident misclassification, reflecting error containment through architectural isolation rather than intrinsic model robustness. These results demonstrate that cascade architectures can operationalize safety-oriented decision constraints through calibrated routing in settings where reliability matters more than aggregate accuracy. These properties depend on threshold calibration and deployment conditions and do not constitute guarantees under arbitrary distribution shift.
Comments44 pages, 7 figures, 12 tables. Submitted to Computers and Electronics in Agriculture, April 2026
