Climate change is currently harming the agricultural sector, causing sea-level rise that has encroached on the land as well as increased precipitation that has led to the extension of floodplains and the reduction in existing croplands ^[1]. On the other hand, rising temperatures have harmed crop production and sustainability nationally and globally ^[2]. According to Nguyen et al., warming trends will likely reduce agricultural production yields in the future unless there is a compelling adaptation ^[2].

Crop losses will increase due to rainfall variability, extreme heat, and flooding, causing resilience problems in arable areas. Furthermore, even high rainfall can hinder harvesting and reduce crop quality ^[3]. Therefore, an adaptation to resilience for agricultural systems should be a policy priority ^[2]. Furthermore, climate change scenarios suggest that warming will generally reduce the sustainability of major staple crops, such as maize and wheat, with higher-yield losses in tropical regions ^[4].

On the other hand are the growing demand for food and other problems the world faces, such as the ability to appropriate new lands, new waters, or new fishing grounds. Furthermore, in addition to the rapid transformation of the earth’s natural systems, climate change, associated with the increase in more extreme temperatures and precipitation, can alter the relations between crops, plagues, pathogens, and weeds, exacerbating several trends, such as reducing pollinating insects, increasing water shortages and ozone concentrations at ground level, and reducing fishing ^[4].

The pressures of the growing population and urbanization, which threaten food safety, have a more significant impact in the context of climate change ^[2]. In light of climate change, guaranteeing food for the global population is no easy task due to its enormous impact on agricultural production ^[5].

The research program of the Consultative Group on International Agricultural Research (CGIAR) ^[6] on climate change, agriculture, and food safety has proposed a framework with four interconnected areas of action for the reconfiguration of food systems: redirecting agricultural trajectories; increasing the resilience of all the agents involved in rapid change; minimizing the environmental footprint of food systems from the point of view of climate change; and realigning the facilitators of change ^[7]. Through this framework, some synergies between food safety, adaptation, and mitigation are feasible, called “climate-smart agriculture”, which is key to this food system transformation ^[7]. The primary goal is to generate actions in agriculture to sustainably increase productivity, improve resilience and adaptation, reduce or eliminate greenhouse gases, increase mitigation, and improve the achievement of international food safety objectives ^[4].

Because of these actions, it is necessary to analyze and better understand the complexities of multivariate and unpredictable agricultural ecosystems ^[8]. The emerging digital technologies mentioned, such as machine learning, the Internet of Things (IoT), and Big Data, contribute to this understanding through the pursuit and continuous measurement of various aspects of the physical surroundings, producing large amounts of data at an unprecedented rate ^[9]. This involves compiling, storing, processing, modeling, and analyzing enormous amounts of data from various heterogeneous sources ^[8].

The earth is a complex, dynamic system such as no one has ever studied before. Thus, the progress of Big Data in climate science has been slower than the success of Big Data in other fields, such as biology or advertising ^[8]. The slow progress has been a stumbling block since climatology has become one of the fields richest in data in terms of volume, speed, and variety ^[8]. Given that the earth is a vast dynamic system, the learning process is developing, and therefore, the understanding of its systems is not as advanced as in other fields that use Big Data ^[10]. Although observation methods originally collected climate data, and the readings had to be manually corroborated, now the data are increasingly younger. In most cases, the data are available in real-time ^[10]. The use of sensors and satellites has revolutionized the process of climate data collection and study, which is a significant contribution.

E. Hassani et al. ^[11] present some advances using Big Data to solve energy efficiency problems, smart agriculture, smart urban planning, weather forecasting, and natural disaster management. Agricultural Big Data addresses various analysis issues in smart agriculture, such as weather forecasting and monitoring crop plagues and animal diseases. Various algorithms, approaches, and diverse techniques are used ^[12].

Agricultural Big Data is still an area of development that can improve productivity in farming operations by using precision agriculture, data-based agriculture, smart agriculture, and predictive modeling ^[13], facilitating intelligent agricultural solutions from a climate point of view in the face of climate change and the effects of natural disasters ^[14].

One crucial challenge is the design of Big Data architectures, as this is not an easy task [15,16,17]^[15][16][17]. It will be even more complex to build architectures for Agricultural Big Data in the context of climate change [9,14]^[9][14]. A. del Pozo et al., propose a multidisciplinary approach, where agronomists, physiologists, molecular biologists, sociologists, economists, and other social scientists must contribute with specific tools to understand complex agricultural systems. This approach can be applied in the different regions of the world, where climate change threatens the future of sustainable agriculture in danger ^[18]. On the other hand, the dynamism and complexity of climate issues that entail an interdisciplinary approach and the interweaving of various disciplines must not be neglected. According to Sebestyen et al., a System of Systems is urgently required, called “climate computation” ^[19]. According to the authors, to resolve any of the challenges related to climate change, “it is essential to obtain and integrate knowledge in an entire series of systems that serve as the basis for the design of solutions that take the complex and uncertain nature of individual systems and their interrelations into account” ^[19].

In this sense, Agricultural Big Data in climate change is one of the critical answers to these needs. This research aims to discuss the advancement of technologies used in Agricultural Big Data architectures in the context of climate change. These study aimscontents aim to highlight the tools used to process, analyze, and visualize the data, to discuss the use of the architectures in crop, water, climate, and soil management, and especially to analyze the context, whether it is in Resilience Mitigation or Adaptation. We provide a A schema that summarizes the data was provided in here, allowing researchers to decide which Big Data solution to use depending on climate change and agriculture issues. In addition, this document allows uresearchers to identify research gaps and opportunities in this area.

2. Agricultural Big Data

Big Data is defined in four dimensions (four Vs). First, it refers to the enormous volume of generated, stored, and processed data. Second, it also refers to the high velocity of data transmission in interactions and the rates at which data are generated, collected, and exchanged. Third, it relates to the variety of data formats and structures (structured, semi-structured, and unstructured) that result from the heterogeneity of data sources ^[20]. Finally, the fourth dimension is veracity, which refers to the ability to validate the data quality used in the analyses. Big Data analysis tools enable data scientists to discover correlations and patterns by analyzing massive quantities of data from different sources. In recent years, the science of Big Data has become an essential modern discipline for data analysis ^[21]. It is considered an amalgam of classic fields, such as statistics, artificial intelligence, mathematics, and informatics with its sub-disciplines, including database systems, ML, and distributed systems ^[22]. The Big Data Ecosystem handles the evolution of data and models and supports infrastructure throughout its life cycle; it is a whole set of components, or architecture, storing, processing, and visualizing data and delivering results to guide applications [23,24]^[23][24]. For example, the Framework Architecture of Big Data in Figure 1 includes data storage, information management, data processing, data analysis, and interface and visualization components. As shown in Figure 1, the Big Data process starts with identifying the sources from which valuable data are extracted ^[25]. Next, the data are stored in one of the designed models, depending on whether the data are structured. In the following step, the data are classified and filtered according to the type of analysis required. In the Processing stage, it is defined whether it will be by Bath or Stream, in addition to the memory-based storage ^[26]. Next, the classified data are analyzed using appropriate tools, for example, DL ^[27], ad hoc analysis ^[28], and data science in general ^[29]. Next, the data obtained must be presented through some visualization tool. Finally, the data are analyzed by the decision-makers ^[24]. Big Data has been used to improve various aspects of agriculture, such as knowledge about weather and climate change, land, animal research, crops, soil, weeds, food availability and security, biodiversity, farmers’ decision making, farmers’ insurance and finance, and remote sensing ^[8]. It is also used to create platforms that allow the supply chain actors to access high-quality products and processes, tools to improve yields and predict demand, and advice and guidance for farmers based on the response capacity of their crops to fertilizers, leading to better fertilizer use.

3. Climate Change

Climate change is one of the most significant global challenges at present. It is defined as the significant changes in the mean values of weather elements, such as precipitation and temperature, which have been calculated for a long time ^[28]. Recent decades indicate that significant global climate changes resulted from increased human activities that altered the composition of the global atmosphere ^[29]. The concentrations of greenhouse gases, such as methane (CH₄), carbon dioxide (CO₂), and nitrous oxide (N₂O), have increased by 150%, 40%, and 20%, respectively, since 1750 ^[30]. CO₂ emissions, representing the maximum proportion of greenhouse gases, increased to 36,140 million metric tons in 2014 from 22,150 million metric tons in 1990. The mean global temperature has increased at an average rate of 0.15–0.20 °C per decade since 1975, and for 2021, between 1.4 and 5.8 °C. Greenhouse gas (GHG) emissions, mainly CO₂ from fossil-fuel combustion as well as GHG not related to CO₂, such as N₂O, CH₄, and CFC, contribute to global warming ^[5]. In the 21st century, climate change will become a severe problem, and both developed and developing countries will face negative externalities ^[5]. Agriculture is the sector most vulnerable to climate change due to its enormous size and sensitivity to weather parameters, which has an enormous economic impact ^[5]. The changes in climate phenomena, such as temperature and precipitation, significantly affect crop yields and sustainability. The effect of increasing temperatures, varying precipitation, and CO₂ fertilization varies by crop, location, and magnitude of parameter change. According to the influence of climate variables, crop productivity depends on several variables: crop type and its ability to adapt, the climate scenario, and the effect of fertilization with CO₂ ^[31]. Nguyen et al., studied the effects of climate change perceived by farmers in different countries ^[2]. The authors report effects such as changes in precipitation patterns and atmospheric temperatures as being most frequently perceived by farmers in Asia. On the other hand, the authors indicate that farmers have noted a trend in increasing temperature and changes in precipitation. Some farmers perceive a decrease, whereas others show an increase in precipitation. In some places, the changes in precipitation have been described as more erratic, unpredictable, and untimely. The authors conclude that farmers’ perceptions of climate change have been consistent with the scientific data observed. In addition, the expected impacts of climate change identified were frequent droughts and floods, cyclones, heat waves, droughts, cold snaps, and soil erosion ^[2]. According to Malhi, the increased intensity and frequency of precipitation also affects soil erosion and will have more adverse consequences if GHGs increase. Moreover, the precipitation anomalies have detrimental effects on agriculture, mainly in developing countries. In addition to affecting crop yields, they significantly influence crop surfaces ^[5]. The studies identified by Nguyen et al., showed that farmers had used different technologies to adjust their land-use options and management practices to climate change. The leading adaptation technologies are used for soil management, water management, crop management, and changes in land-use options ^[2]. Some examples of these technologies include crop residues, such as topsoil, minimization of plowing and reduction in tillage as soil conservation strategies, deep plowing during the rainy season, rainwater collection for use during the dry season, and others. According to the Intergovernmental Panel on Climate Change ^[32], adaptation is adjusting to current or projected climate change and its consequences to minimize damage or take advantage of good opportunities. On the other hand, resilience is a process of recovery of the previous condition after facing any adverse effect or the adaptive, absorptive, and transformative capacity of a social unit, such as an individual community or state, to cope with any natural disaster. The resilience perspective is an understanding of the adaptive capacity of a system ^[33]. Adaptation in agriculture is crucial, as it is highly dependent on climate, and some farmers have already started to employ some strategies ^[2]. On the other hand, climate change mitigation means avoiding and reducing GHG emissions, which trap heat in the atmosphere, to prevent the planet from becoming extremely hot. The more we mitigate climate change now, the easier it will be to adapt to changes we can no longer avoid. The potential of Big Data can be a crucial approach to managing the adverse effect of climate change globally, as it enables the development of context-specific adaptation strategies to improve resilience to climate change and appropriate analytics to assist with mitigation ^[33]. With Big Data, it is possible to display information regarding upcoming problems, current ones, and the stages of recovery from the adverse effect of climate change. On the other hand, it is a tool for policymakers, managers, and stakeholders to take necessary actions during and after a disaster, such as an early warning system, weather forecasting, emergency evacuation, immediate responses, and aid distribution ^[33]. To maximize the benefit of Big Data applied to climate change, the authors conclude that there are still challenges to solve, such as data collection, architecture design, ethical and political anomalies, poor team coordination, privacy, and accuracy. They recommend implementing adequate infrastructure, technologies, tools, and knowledge to ensure the proper use of Big Data in climate change ^[33].