Yield forecasting, the science of predicting agricultural productivity before
the crop harvest occurs, helps a wide range of stakeholders make better
decisions around agricultural planning. This study aims to investigate whether
machine learning-based yield prediction models can capably predict Kharif
season rice yields at the district level in India several months before the
rice harvest takes place. The methodology involved training 19 machine learning
models such as CatBoost, LightGBM, Orthogonal Matching Pursuit, and Extremely
Randomized Trees on 20 years of climate, satellite, and rice yield data across
247 of Indian rice-producing districts. In addition to model-building, a
dynamic dashboard was built understand how the reliability of rice yield
predictions varies across districts. The results of the proof-of-concept
machine learning pipeline demonstrated that rice yields can be predicted with a
reasonable degree of accuracy, with out-of-sample R2, MAE, and MAPE performance
of up to 0.82, 0.29, and 0.16 respectively. These results outperformed test set
performance reported in related literature on rice yield modeling in other
contexts and countries. In addition, SHAP value analysis was conducted to infer
both the importance and directional impact of the climate and remote sensing
variables included in the model. Important features driving rice yields
included temperature, soil water volume, and leaf area index. In particular,
higher temperatures in August correlate with increased rice yields,
particularly when the leaf area index in August is also high. Building on the
results, a proof-of-concept dashboard was developed to allow users to easily
explore which districts may experience a rise or fall in yield relative to the
previous year.

通过训练 19 个基于机器学习的模型，研究使用气候、卫星和稻谷产量数据预测印度 Kharif 季稻谷产量，结果表明可以以相当准确的水平进行预测，并通过分析推断出气候和遥感变量对稻谷产量的重要性和方向影响，最终开发出一个证明性仪表盘以便用户探索各个地区的产量变化。

利用气候再分析数据对印度区级基于机器学习的水稻产量预测的可行性研究

Feasibility of machine learning-based rice yield prediction in India at  the district level using climate reanalysis data

Residential buildings account for a significant portion (35\%) of the total
electricity consumption in the U.S. as of 2022. As more distributed energy
resources are installed in buildings, their potential to provide flexibility to
the grid increases. To tap into that flexibility provided by buildings,
aggregators or system operators need to quantify and forecast flexibility.
Previous works in this area primarily focused on commercial buildings, with
little work on residential buildings. To address the gap, this paper first
proposes two complementary flexibility metrics (i.e., power and energy
flexibility) and then investigates several mainstream machine learning-based
models for predicting the time-variant and sporadic flexibility of residential
buildings at four-hour and 24-hour forecast horizons. The
long-short-term-memory (LSTM) model achieves the best performance and can
predict power flexibility for up to 24 hours ahead with the average error
around 0.7 kW. However, for energy flexibility, the LSTM model is only
successful for loads with consistent operational patterns throughout the year
and faces challenges when predicting energy flexibility associated with HVAC
systems.

该研究提出了两种互补的灵活性测量指标，并使用主流的基于机器学习的模型预测住宅建筑物在四小时和 24 小时预测时段内的时间变化和间歇性灵活性。长短期记忆（LSTM）模型在功率灵活性方面表现最佳，可以在 24 小时内准确预测功率灵活性，平均误差约为 0.7 千瓦。然而，在能源灵活性方面，LSTM 模型只能成功预测具有一致运行模式的负荷，并且在预测与暖通空调系统相关的能源灵活性时面临挑战。