"Recently Emerging Trends in Big Data Analytic Methods for Modeling and Combating Climate Change Effects"

 

Fig. 2

    This literature review by Ikegwu et al. (2024) examines how big data analysis can help us understand and fight climate change. The paper gives thought to other ways of analyzing huge amounts of climate data and weighs the advantages and the disadvantages of each method. While the paper deals with a timely topic, there are certain issues regarding the research design and presentation.

    The article is dealing with a critically important topic. Climate change is one of the biggest problems we face today, and using big data to become more familiar with it is understandable. Ikegwu et al. (2024) effectively classify different types of data analytics methods and outline what each does. They also provide a useful summary of climate data sources, including satellites, weather stations, and computer models. The article is clearly organized with clear headings that make it easy to read. Ikegwu et al. (2024) tackle both traditional methods like statistical models and newer methods like machine learning and artificial intelligence. They also address real-world applications, such as disease prediction under climate change and monitoring of crop growth.

    However, one of the significant problems with this paper is that while it quotes many studies, the authors are not clear about what their search strategy was or how they chose the literature that they reviewed. The paper is not clear on how they found and chose the studies that they included, and it is therefore difficult to know if their review is exhaustive or if they left out key research (Ikegwu et al., 2024). Without a methodology section describing their search, databases, and inclusion criteria, readers cannot evaluate the reliability and comprehensiveness of their findings. The paper mainly describes several approaches but does not critically evaluate their performance. Although Ikegwu et al. (2024) list strengths and weaknesses in tables, they do not provide comprehensive analysis of when each approach works or does not work. For example, they describe machine learning approaches but do not compare how well each performs relative to traditional approaches through real data.

    Another concern is that the authors indicate their study covers a gap in the literature, but do not clearly show how they deliver something new. Much of the information seems to simply echo what is currently known about big data and climate change. The paper would be more persuasive if it described some of the problems existing approaches cannot solve or proposed new approaches. Though Ikegwu et al. (2024) discuss extremely numerous disparate topics, sometimes it is too nontechnical in specificity to be useful to researchers or practitioners. For instance, when the authors are referring to machine learning algorithms, they cite such techniques as support vector machines and decision trees without explaining when to use each of these or how each can be differentiated in climate contexts.

    The paper does not satisfactorily report data quality and validation issues. Climate data contain missing values, measurement flaws, and biases affecting analytical outputs (Ikegwu et al., 2024). These challenges are noted by the authors superficially, but they do not discuss how different analytics methods address these concerns. A few essential issues are omitted in this review. The article does not talk about the ethical issues of using big data in climate studies, like privacy problems when using social media or satellite images. It also does not mention the energy and resources needed for computing, which is surprising since the topic is about protecting the environment.

Fig. 3

    Ikegwu et al. (2024) are not providing enough information on how effective these methods have been in actual application. While they refer to some examples, they do not evaluate the results critically or address any limitations. To make this study more helpful, the authors must expand their literature search to encompass more sources and provide a clear study selection methodology. Ikegwu et al. (2024) could do better by showing more critical comparison among different methodologies, such as their efficacy and scopes of knowledge gaps. The review would be further enriched by having more reference to practical issues, such as data amalgamation from different sources and computational capability involved for different strategies. Adding case studies with achievements and mishaps would make the review more well-rounded and valuable.

While this paper addresses an important theme and offering a useful summary of the big data strategy for climate science, it is not a full literature review. The limited range, lack of critique, and omission of methodology details make it less useful for researchers and practitioners. The topic calls for more comprehensive and rigorous treatment to enable the improved direction of future research and applied work in this important area.

References

Ikegwu, A. C., Nweke, H. F., Mkpojiogu, E., Anikwe, C. V., Igwe, S. A., & Alo, U. R. (2024). Recently emerging trends in big data analytic methods for modeling and combating climate change effects. Energy Informatics, 7(1), 1-28. https://doi.org/10.1186/s42162-024-00307-5