When less is more: How increasing the complexity of machine learning strategies for geothermal energy assessments may not lead toward better estimates
When less is more: How increasing the complexity of machine learning strategies for geothermal energy assessments may not lead toward better estimates
复制标题
当少即是多时：增加地热能评估机器学习策略的复杂性可能不会带来更好的估计
DOI：
10.1016/j.geothermics.2023.102662
复制
发表时间：
2023
期刊：
影响因子：
3.9
通讯作者：
Lindsey, Cary R.
中科院分区：
文献类型：
--
作者：
Mordensky, Stanley P.;Lipor, John J.;DeAngelo, Jacob;Burns, Erick R.;Lindsey, Cary R.
美国西部以前的中高温地热资源评估利用数据驱动的方法和专家决策来估计资源可利用性。虽然专家决策可以通过确保采用合理的模型来增加建模过程的信心，但专家决策也会引入人为偏差，从而引入模型偏差。这种偏差可能是一个错误的来源，降低了模型的预测性能和对资源估计结果的信心。我们的研究旨在开发强大的数据驱动方法，以减少偏差和提高预测能力。我们提出并比较九个地热资源的可扩展性地图在美国西部使用的数据从美国地质调查局的2008年地热资源评估。使用2008年评估中的专家决策依赖方法创建了两个可扩展性图（即，证据权重和逻辑回归）。使用相同的数据，我们使用逻辑回归（没有潜在的专家决策），XGBoost和支持向量机与两种训练策略配对创建六个不同的可扩展性图。训练策略是定制的，以解决将机器学习应用于地热训练数据的固有挑战，这些数据没有负面示例和严重的类别不平衡。我们还使用人工神经网络创建了另一个可扩展性图。我们证明了现代机器学习方法可以改进由专家决策构建的系统。我们还发现，XGBoost（一种非线性算法）比没有专家决策的线性逻辑回归与2008年结果的一致性更高，因为2008年评估中的专家决策使原本线性的方法变得非线性，尽管事实上2008年评估仅使用线性方法。所有方法的F1得分都很低（F1得分< 0.10），不会随着模型复杂性的增加而改善，因此，表明输入特征的基本限制（即，训练数据）。在改进的特征数据被纳入评估过程之前，简单的非线性算法（例如，XGBoost）与更复杂的方法（例如，人工神经网络）并且保持更容易解释。
Previous moderate- and high-temperature geothermal resource assessments of the western United States utilized data-driven methods and expert decisions to estimate resource favorability. Although expert decisions can add confidence to the modeling process by ensuring reasonable models are employed, expert decisions also introduce human and, thereby, model bias. This bias can present a source of error that reduces the predictive performance of the models and confidence in the resulting resource estimates.Our study aims to develop robust data-driven methods with the goals of reducing bias and improving predictive ability. We present and compare nine favorability maps for geothermal resources in the western United States using data from the U.S. Geological Survey's 2008 geothermal resource assessment. Two favorability maps are created using the expert decision-dependent methods from the 2008 assessment (i.e.,weight-of-evidence and logistic regression). With the same data, we then create six different favorability maps using logistic regression (without underlying expert decisions), XGBoost, and support-vector machines paired with two training strategies. The training strategies are customized to address the inherent challenges of applying machine learning to the geothermal training data, which have no negative examples and severe class imbalance. We also create another favorability map using an artificial neural network.We demonstrate that modern machine learning approaches can improve upon systems built with expert decisions. We also find that XGBoost, a non-linear algorithm, produces greater agreement with the 2008 results than linear logistic regression without expert decisions, because the expert decisions in the 2008 assessment rendered the otherwise linear approaches non-linear despite the fact that the 2008 assessment used only linear methods. The F1 scores for all approaches appear low (F1 score < 0.10), do not improve with increasing model complexity, and, therefore, indicate the fundamental limitations of the input features (i.e.,training data). Until improved feature data are incorporated into the assessment process, simple non-linear algorithms (e.g.,XGBoost) perform equally well or better than more complex methods (e.g.,artificial neural networks) and remain easier to interpret.
登录
查看更多内容
DOI：
--
发表时间：
2021
期刊：
影响因子：
--
作者：
Cary R. Lindsey;B. Ayling;G. Asato;R. Seggiaro;N. Carrizo;N. Larcher;Cintia Marquetti;Virginia Naón;A. C. Serra;J. Faulds;M. Coolbaugh
通讯作者：
M. Coolbaugh
影响因子：
7.5
作者：
Bekker, Jessa;Davis, Jesse
通讯作者：
Davis, Jesse
美国地热资源评估，1978 年
DOI：
--
发表时间：
1979
期刊：
影响因子：
--
作者：
L. Muffler
通讯作者：
L. Muffler
北美西部火山岩和侵入岩地球化学数据库 (NAVDAT)
DOI：
10.1130/2006.2397(05
发表时间：
2006
期刊：
Encyclopedia of Gerontology and Population Aging
影响因子：
--
作者：
J. Walker;T. Bowers;R. Black;A. Glazner;G. L. Farmer;R. Carlson
通讯作者：
R. Carlson
影响因子：
3.9
作者：
N. Lautze;G. Ito;D. Thomas;N. Frazer;S. Martel;N. Hinz;Diamond K. Tachera;G. Hill;H. Pierce;P. Wannamaker;T. Martin
通讯作者：
N. Lautze;G. Ito;D. Thomas;N. Frazer;S. Martel;N. Hinz;Diamond K. Tachera;G. Hill;H. Pierce;P. Wannamaker;T. Martin