研究：机器学习施肥推荐中的算法单一化风险
Algorithmic Monoculture in Machine Learning-based Site-Specific Fertilizer Recommendation
摩洛哥 5 个谷物系统的数据建模发现，农场都堆同一个施肥模型会让误差叠加，多样化组合能降 10%-40% 的社会损失。
一项针对 NPK 施肥处方的研究指出，多个农场采用同一模型时，相关误差会叠加产生系统性损失。研究构建了将社会损失与模型采用份额关联的模型，用 HHI 指数刻画集中度效应，并提出两模型阈值判断私有最优的单一化何时在社会层面被支配。基于摩洛哥 5 个谷物系统的 9 个模型家族进行校准，在 10% regret 上限约束下，准确性约束的多样化使 5 个系统的模型化社会损失降低 10.89%-41.53%，均值 19.41%。敏感性分析显示，模型误差高度相关时会削弱多样化的收益。
Algorithmic Monoculture in Machine Learning-based Site-Specific Fertilizer Recommendation
Machine learning recommendations are often evaluated one model at a time, despite deployment across interconnected decision makers. For continuous NPK fertilizer prescriptions, correlated errors can aggregate across farms and generate systemic costs. A model of shared and farm-specific recommendation errors links expected social loss to model adoption shares; the Herfindahl-Hirschman Index characterizes concentration effects when common model errors are independent and predictive risks are equal. A covariance-generalized formulation captures the dependence between model families. A two-model threshold characterizes when privately optimal monoculture is socially dominated, and a convex portfolio rule limits average private predictive regret. Nine model families across five Moroccan cereal systems provide a benchmark-based calibration. Under illustrative parameters and a 10% regret cap, accuracy-constrained diversification lowers modeled social loss in all five systems by 10.89-41.53% (mean 19.41%). Uniform allocation reduces modeled loss in this setting, but breaches the regret cap in every crop. Correlation sensitivity shows that highly dependent model errors attenuate the benefits of diversification. These counterfactual outcomes are not estimates of agronomic or monetary welfare; the framework identifies adoption architecture and error dependence as ecosystem-level evaluation variables.