Khan Sidra, Akram Beenish Ayesha, Zafar Amna, Wasim Muhammad, Khurshid Khaldoon S, Pires Ivan Miguel
Department of Computer Engineering, University of Engineering and Technology Lahore, Lahore, Pakistan.
Department of Computer Science, University of Engineering and Technology Lahore, Lahore, Pakistan.
PeerJ Comput Sci. 2024 Oct 28;10:e2420. doi: 10.7717/peerj-cs.2420. eCollection 2024.
The desert locust is one of the most destructive locusts recorded in human history, and it has caused significant food shortages, monetary losses, and environmental calamities. Prediction of locust attacks is complicated as it depends on various environmental and geographical factors. This research aims to develop a machine-learning model for predicting desert locust attacks in 42 countries that considers three predictors: soil moisture, maximum temperature, and precipitation. We developed the Global Locust Attack Database for 42 countries (GLAD42) by integrating TerraClimate's environmental data with locust swarm attack data from the Food and Agriculture Organization (FAO). To improve the usability of spatial data, reverse geocoding which is the process of converting geographic coordinates (longitude and latitude) into human-readable location names (such as countries and regions) was employed. This step enhances the clarity and interpretability of the data by providing meaningful geographic context. This study's initial dataset focused on instances where locust attacks were recorded (positive class). To ensure a comprehensive analysis, we also incorporated negative class instances, representing periods (specific years and months) in the same countries and regions where locust attacks did not occur. This research utilizes the benefits of lazy learners by employing the K-nearest neighbor algorithm (K-NN), which provides high accuracy and the benefit of no time-consuming retraining even if real-time updated data is periodically added to the system. This research also focuses on building an eco-friendly machine learning model by evaluating carbon emissions from ML models. The results obtained from LocustLens are compared with other machine learning models, including baseline-K-NN, decision trees (DT), Logistic regression (LR), AdaBoost Classifier, BaggingClassifier, and support vector classifier (SVC). LocustLens outperformed all competitors with an accuracy of 98%, while baseline-K-NN achieved 96%, SVC gave 91%, DT gave 97%, AdaBoost has accuracy of 91%, BaggingClassifier gave 94% and LR gave 83%, respectively. Carbon emissions from RAM and CPU electricity consumption are measured in kg gCO2. They are a minimum for AdaBoost Classifier equal to 0.02 and 0.07 for DT and a maximum of 9.03 for SVC. The carbon footprint of LocustLens is 4.87 kg gCO.
沙漠蝗虫是人类历史上有记录的最具破坏力的蝗虫之一，它造成了严重的粮食短缺、经济损失和环境灾难。蝗虫袭击的预测很复杂，因为它取决于各种环境和地理因素。本研究旨在开发一种机器学习模型，用于预测42个国家的沙漠蝗虫袭击情况，该模型考虑了三个预测因素：土壤湿度、最高温度和降水量。我们通过将TerraClimate的环境数据与联合国粮食及农业组织（粮农组织）的蝗虫群袭击数据相结合，开发了42个国家的全球蝗虫袭击数据库（GLAD42）。为了提高空间数据的可用性，采用了反向地理编码，即将地理坐标（经度和纬度）转换为人类可读的地点名称（如国家和地区）的过程。这一步骤通过提供有意义的地理背景，增强了数据的清晰度和可解释性。本研究的初始数据集侧重于记录蝗虫袭击的实例（正类）。为了确保全面分析，我们还纳入了负类实例，即代表同一国家和地区未发生蝗虫袭击的时期（特定年份和月份）。本研究利用了懒惰学习器的优势，采用了K近邻算法（K-NN），该算法具有很高的准确性，并且即使系统定期添加实时更新的数据，也无需进行耗时的重新训练。本研究还专注于通过评估机器学习模型的碳排放来构建一个生态友好型的机器学习模型。将LocustLens获得的结果与其他机器学习模型进行比较，包括基线K-NN、决策树（DT）、逻辑回归（LR）、AdaBoost分类器、BaggingClassifier和支持向量分类器（SVC）。LocustLens的准确率为98%，优于所有竞争对手，而基线K-NN的准确率为96%，SVC为91%，DT为97%，AdaBoost的准确率为91%，BaggingClassifier为94%，LR为83%。随机存取存储器（RAM）和中央处理器（CPU）电力消耗产生的碳排放量以千克二氧化碳当量（kg gCO2）为单位进行测量。AdaBoost分类器的碳排放量最低，为0.02，DT为0.07，SVC最高，为9.03。LocustLens的碳足迹为4.87 kg gCO₂。
