【目的】本研究旨在探讨构建抑郁严重度预测模型及其解释性问题，通过分析互联网用户生成的内容，进一步发展抑郁症风险预测研究，从而提高抑郁症自动检测模型的可靠性和实用性。【方法】通过收集“好大夫在线”平台上的抑郁症医疗咨询文本记录，构建了一个语料库。利用心理学词典，从中提取了患者的心理特征，并采用梯度提升树算法预测患者的病情，同时引入可解释机器学习方法SHAP解读模型，借助SHAP独特的可视化图表剖析患者年龄、性别、认知、情感、感知、社会家庭及个人得失与抑郁症发生之间的复杂关系。【结果】抑郁症患者心理状态能反馈患者病况，利用从患者问诊记录中提取的心理特征能够有效检测重度抑郁，准确率达到86%。可解释机器学习模型SHAP解释了模型的预测结果，揭示出患者各层面心理特征对抑郁症发生产生的多重效应。【局限】受语料集所限，仅利用单次问诊记录对抑郁程度做预测；而模型特征基于心理学词典，更多与抑郁症发生风险有关的要素可纳入建模考虑中。【结论】影响抑郁症产生及发展的因素复杂。个体差异致使各项特征对于疾病预测产生不同效应。构建抑郁症的自动诊断模型，不仅要关注模型的精准度，更需增强对模型预测的理解。

Fire is a worldwide phenomenon that appears in the geological record soon after the appearance of terrestrial plants. Fire influences global ecosystem patterns and processes, including vegetation distribution and structure, the carbon cycle, and climate. Although humans and fire have always coexisted, our capacity to manage fire remains imperfect and may become more difficult in the future as climate change alters fire regimes. This risk is difficult to assess, however, because fires are still poorly represented in global models. Here, we discuss some of the most important issues involved in developing a better understanding of the role of fire in the Earth system.

Human land use practices, altered climates, and shifting forest and fire management policies have increased the frequency of large wildfires several-fold. Mitigation of potential fire behaviour and fire severity have increasingly been attempted through pre-fire alteration of wildland fuels using mechanical treatments and prescribed fires. Despite annual treatment of more than a million hectares of land, quantitative assessments of the effectiveness of existing fuel treatments at reducing the size of actual wildfires or how they might alter the risk of burning across landscapes are currently lacking. Here, we present a method for estimating spatial probabilities of burning as a function of extant fuels treatments for any wildland fire-affected landscape. We examined the landscape effects of more than 72 000 ha of wildland fuel treatments involved in 14 large wildfires that burned 314 000 ha of forests in nine US states between 2002 and 2010. Fuels treatments altered the probability of fire occurrence both positively and negatively across landscapes, effectively redistributing fire risk by changing surface fire spread rates and reducing the likelihood of crowning behaviour. Trade offs are created between formation of large areas with low probabilities of increased burning and smaller, well-defined regions with reduced fire risk.

Artificial intelligence has been applied in wildfire science and management since the 1990s, with early applications including neural networks and expert systems. Since then, the field has rapidly progressed congruently with the wide adoption of machine learning (ML) methods in the environmental sciences. Here, we present a scoping review of ML applications in wildfire science and management. Our overall objective is to improve awareness of ML methods among wildfire researchers and managers, as well as illustrate the diverse and challenging range of problems in wildfire science available to ML data scientists. To that end, we first present an overview of popular ML approaches used in wildfire science to date and then review the use of ML in wildfire science as broadly categorized into six problem domains, including (i) fuels characterization, fire detection, and mapping; (ii) fire weather and climate change; (iii) fire occurrence, susceptibility, and risk; (iv) fire behavior prediction; (v) fire effects; and (vi) fire management. Furthermore, we discuss the advantages and limitations of various ML approaches relating to data size, computational requirements, generalizability, and interpretability, as well as identify opportunities for future advances in the science and management of wildfires within a data science context. In total, to the end of 2019, we identified 300 relevant publications in which the most frequently used ML methods across problem domains included random forests, MaxEnt, artificial neural networks, decision trees, support vector machines, and genetic algorithms. As such, there exists opportunities to apply more current ML methods — including deep learning and agent-based learning — in the wildfire sciences, especially in instances involving very large multivariate datasets. We must recognize, however, that despite the ability of ML models to learn on their own, expertise in wildfire science is necessary to ensure realistic modelling of fire processes across multiple scales, while the complexity of some ML methods such as deep learning requires a dedicated and sophisticated knowledge of their application. Finally, we stress that the wildfire research and management communities play an active role in providing relevant, high-quality, and freely available wildfire data for use by practitioners of ML methods.

Jolly, W. Matt; Freeborn, Patrick H. US Forest Serv, Rocky Mt Res Stn, Fire Sci Lab, Missoula, MT 59803 USA. Cochrane, Mark A.; Freeborn, Patrick H. S Dakota State Univ, GSCE, Brookings, SD 57007 USA. Holden, Zachary A. US Forest Serv Reg 1, Missoula, MT 59802 USA. Brown, Timothy J. Western Reg Climate Ctr, DRI, Reno, NV 89512 USA. Williamson, Grant J.; Bowman, David M. J. S. Univ Tasmania, Sch Biol Sci, Hobart, Tas 7001, Australia.

Tree-based machine learning models such as random forests, decision trees, and gradient boosted trees are popular non-linear predictive models, yet comparatively little attention has been paid to explaining their predictions. Here, we improve the interpretability of tree-based models through three main contributions: 1) The first polynomial time algorithm to compute optimal explanations based on game theory. 2) A new type of explanation that directly measures local feature interaction effects. 3) A new set of tools for understanding global model structure based on combining many local explanations of each prediction. We apply these tools to three medical machine learning problems and show how combining many high-quality local explanations allows us to represent global structure while retaining local faithfulness to the original model. These tools enable us to i) identify high magnitude but low frequency non-linear mortality risk factors in the US population, ii) highlight distinct population sub-groups with shared risk characteristics, iii) identify non-linear interaction effects among risk factors for chronic kidney disease, and iv) monitor a machine learning model deployed in a hospital by identifying which features are degrading the model's performance over time. Given the popularity of tree-based machine learning models, these improvements to their interpretability have implications across a broad set of domains.

Black box machine learning models are currently being used for high stakes decision-making throughout society, causing problems throughout healthcare, criminal justice, and in other domains. People have hoped that creating methods for explaining these black box models will alleviate some of these problems, but trying to black box models, rather than creating models that are in the first place, is likely to perpetuate bad practices and can potentially cause catastrophic harm to society. There is a way forward - it is to design models that are inherently interpretable. This manuscript clarifies the chasm between explaining black boxes and using inherently interpretable models, outlines several key reasons why explainable black boxes should be avoided in high-stakes decisions, identifies challenges to interpretable machine learning, and provides several example applications where interpretable models could potentially replace black box models in criminal justice, healthcare, and computer vision.

Humans influence the frequency and spatial pattern of fire and contribute to altered fire regimes, but fuel loading is often the only factor considered when planning management activities to reduce fire hazard. Understanding both the human and biophysical landscape characteristics that explain how fire patterns vary should help to identify where fire is most likely to threaten values at risk. We used human and biophysical explanatory variables to model and map the spatial patterns of both fire ignitions and fire frequency in the Santa Monica Mountains, a human-dominated southern California landscape. Most fires in the study area are caused by humans, and our results showed that fire ignition patterns were strongly influenced by human variables. In particular, ignitions were most likely to occur close to roads, trails, and housing development but were also related to vegetation type. In contrast, biophysical variables related to climate and terrain (January temperature, transformed aspect, elevation, and slope) explained most of the variation in fire frequency. Although most ignitions occur close to human infrastructure, fires were more likely to spread when located farther from urban development. How far fires spread was ultimately related to biophysical variables, and the largest fires in southern California occurred as a function of wind speed, topography, and vegetation type. Overlaying predictive maps of fire ignitions and fire frequency may be useful for identifying high-risk areas that can be targeted for fire management actions.

The frequent occurrence and spread of wildfires pose a serious threat to the ecological environment and urban development. Therefore, assessing regional wildfire susceptibility is crucial for the early prevention of wildfires and formulation of disaster management decisions. However, current research on wildfire susceptibility primarily focuses on improving the accuracy of models, while lacking in-depth study of the causes and mechanisms of wildfires, as well as the impact and losses they cause to the ecological environment and urban development. This situation not only increases the uncertainty of model predictions but also greatly reduces the specificity and practical significance of the models. We propose a comprehensive evaluation framework to analyze the spatial distribution of wildfire susceptibility and the effects of influencing factors, while assessing the risks of wildfire damage to the local ecological environment and urban development. In this study, we used wildfire information from the period 2013–2022 and data from 17 susceptibility factors in the city of Guilin as the basis, and utilized eight machine learning algorithms, namely logistic regression (LR), artificial neural network (ANN), K-nearest neighbor (KNN), support vector regression (SVR), random forest (RF), gradient boosting decision tree (GBDT), light gradient boosting machine (LGBM), and eXtreme gradient boosting (XGBoost), to assess wildfire susceptibility. By evaluating multiple indicators, we obtained the optimal model and used the Shapley Additive Explanations (SHAP) method to explain the effects of the factors and the decision-making mechanism of the model. In addition, we collected and calculated corresponding indicators, with the Remote Sensing Ecological Index (RSEI) representing ecological vulnerability and the Night-Time Lights Index (NTLI) representing urban development vulnerability. The coupling results of the two represent the comprehensive vulnerability of the ecology and city. Finally, by integrating wildfire susceptibility and vulnerability information, we assessed the risk of wildfire disasters in Guilin to reveal the overall distribution characteristics of wildfire disaster risk in Guilin. The results show that the AUC values of the eight models range from 0.809 to 0.927, with accuracy values ranging from 0.735 to 0.863 and RMSE values ranging from 0.327 to 0.423. Taking into account all the performance indicators, the XGBoost model provides the best results, with AUC, accuracy, and RMSE values of 0.927, 0.863, and 0.327, respectively. This indicates that the XGBoost model has the best predictive performance. The high-susceptibility areas are located in the central, northeast, south, and southwest regions of the study area. The factors of temperature, soil type, land use, distance to roads, and slope have the most significant impact on wildfire susceptibility. Based on the results of the ecological vulnerability and urban development vulnerability assessments, potential wildfire risk areas can be identified and assessed comprehensively and reasonably. The research results of this article not only can improve the specificity and practical significance of wildfire prediction models but also provide important reference for the prevention and response of wildfires.