Explainable Artificial Intelligence and Interpretable Machine Learning for Agricultural Data Analysis

Arti fi cial intelligence and machine learning have been increasingly applied for prediction in agricultural science. However, many models are typicallyblack boxes,meaning wecannot explainwhat the modelslearnedfrom the data and the reasons behind predictions. To address this issue, I introduce an emerging subdomain of arti fi cial intelligence, explainable arti fi cial intelligence (XAI), and associated toolkits, interpretable machine learning. This study demonstrates the usefulness of several methods by applying them to an openly available dataset. Thedatasetincludes the no-tillage effect oncropyield relative to conventional tillageandsoil, climate,andman-agement variables. Data analysis discovered that no-tillage management can increase maize crop yield where yield in conventional tillage is <5000 kg/ha and the maximum temperature is higher than 32°. These methods are useful to answer (i) which variables are important for prediction in regression/classi fi cation, (ii) which var-iableinteractionsareimportantforprediction,(iii)howimportantvariablesandtheirinteractionsareassociated with the response variable, (iv) what are the reasons underlying a predicted value for a certain instance, and (v) whether different machine learning algorithms offer the same answer to these questions. I argue that the goodness of model fi t is overly evaluated with model performance measures in the current practice, while these questions are unanswered. XAI and interpretable machine learning can enhance trust and explainability in AI. © 2022 The Author. Publishing services by Elsevier B.V. on behalf of KeAi Communications Co., Ltd. This is