Integration of Technology in Agricultural Practices towards Agricultural Sustainability: A Case Study of Greece

The mechanisms controlling the application of innovations include dissemination and adoption. One way to think about diffusion is as extensive, aggregate adoption. A considerable amount of time passes between new technology’s creation and farmers’ acceptance of it [16,17]. Many variables may influence how new technology is adopted. Numerous elements that affect the adoption of technology are mentioned in the extensive literature on this subject [18]. The qualities of the technology, the farmer’s goal, the traits of the change agent, and the socioeconomic, biological, and physical context in which the technology is introduced are some of the elements that influence the degree of technology adoption [6]. A farmer’s age, level of education, income, family size, tenure status, usage of credit, value system, and beliefs are sociopsychological characteristics that are positively correlated with adoption [19,20]. In addition, the farmers’ ability to adapt may also be influenced by the personality of the local extension agents. Adoption is influenced by the reputation, relationship with farmers, and communication skills of extension agents working in tandem with the efficiency of the technology transfer process. Furthermore, the biophysical aspects of the agricultural region, such as the infrastructure and resources available to the farm, have a favorable impact on the social network of the farmers [8,21].

Furthermore, an adoption category based on the innovation decision period has been highlighted by Yépez–Ponce et al. (2021) [22]. The amount of time needed to complete the innovation–decision process is known as the innovation–decision period. A person’s choice to embrace an invention is determined by how long it takes them to become aware of it—this might take days, months, or years [23,24]. Furthermore, the steps of the decision-making process are shown by Rogers’ (1983) [25] innovation decision model [26,27,28]. These stages include learning about an innovation for the first time, deciding whether to accept or reject it, putting the new concept into practice if it is accepted, and verifying this choice [22].

Technology adoption among farmers depends on the dissemination of technology-related information [24,29]. Farmers often have conservative views and need a lot of time and knowledge to be convinced to use new technology [30]. Technical direction and trustworthy information are necessary for the effective commercialization of new innovations and technologies. Hence, farmers who are unsure about using new technology will find it easier to convince themselves with the help of demonstration plots and nearby farmers who have already made the switch. Farmers may benefit from the useful information that demonstration plots can provide to help them smoothly adopt new technologies [31].

Precision agriculture, often known as smart agriculture, is a system that combines cutting-edge smart technology with conventional agricultural methods to increase both the amount and quality of agricultural output [1]. Smart agriculture-use methods that are different from traditional ones, such as controlled irrigation and targeted, accurate application of herbicides and fertilizers, are used to raise production, decrease environmental impact, and increase efficiency and profitability [11,32,33]. Crops are severely impacted by a number of factors, including the soil, pests, diseases, and environment. This lowers production quality and quantity and causes major economic losses, as well as food emergencies. Right now, precision agriculture tries to provide answers. But the issue that emerges and worries us greatly is whether artificial intelligence (AI) can really assist in resolving the worldwide crop loss that imperils the planet’s food security [7].

Dhanaraju et al. (2022) [34] noted that artificial intelligence, big data, cloud and edge computing, smart sensors, Internet of Things (IoT) technology, robots, drones, and artificial intelligence are the primary digital technologies enabling the development and implementation of smart agricultural systems. The next phase of industrial agriculture, often described as “Agriculture 4.0”, or “precision, smart, or digital agriculture”, is powered by the integration of these technologies into the agricultural sector [6]. Nonetheless, a number of issues that must be addressed in the developing area of smart agriculture should be brought to light, including digitalization, the agricultural supply chain, ecological issues, and crop production [32,33].

Recent developments in smart agriculture, which make use of machinery, equipment, sensors, information technology, and computer vision, set them apart from conventional agricultural methods in a big way [6]. Aerial imaging, humidity sensors, robotics, GNSS, and other cutting-edge equipment and technology will be crucial to agriculture in the future. A decision-support system may optimize food supply chains, identify crop diseases, allocate resources more efficiently, and adjust to climate change in real time [35]. As an artificial intelligence method, fuzzy logic (FL) enables a controller to accurately perceive changes over time so that judgments may be made and actions taken in real time [6]. The FL approach is now extensively employed in the agricultural industry for a variety of purposes, including guiding robots used for harvesting and unmanned aerial vehicle (UAV) navigation for farm monitoring from above and picture capturing that is analyzed to make choices [6,36].

The real-time kinematic (RTK) technique is a satellite navigation method that is employed to improve the precision of location information for real-time applications. RTK achieves centimeter-level precision in determining the location of an object that is moving, such as an automotive or a surveying instrument, by employing a network of stationary base stations that transmit signals and mobile receivers. The methodology operates by conducting a comparative analysis between the timing of the carrier signal emitted by satellites and the phase received by the receiver. This process effectively mitigates errors arising from atmospheric conditions and various sources of interference [37,38,39].

AI technologies are being used in agriculture in a variety of contexts, altering conventional agricultural methods. These are a few major fields where AI is having a big influence [7,40,41]. Artificial intelligence (AI) technologies, such as computer vision, robotics, natural language processing, and machine learning, have been integrated into tech business models in recent years. Applications of AI have the potential to lower costs associated with supporting smallholder farmers throughout the agriculture ecosystem, enhance the sustainable and efficient use of resources, and eliminate market asymmetries that keep farmers from participating in regional and global value chains. Examples of these applications include “smart” farm equipment and alternative credit scoring [40,42]. Due to developments in big-data analytics, cloud computing, and computing power, as well as lower costs for satellite imagery, remote sensors, and other hardware (like smartphones), mobile connectivity has become more accessible and affordable, making the use of AI technologies for agriculture commercially viable in recent years [43].

AI integrates real-time data from several sources, such as drones, Internet of Things sensors, and satellite photography, to allow precision agriculture. These data are analyzed by machine-learning algorithms, which provide insightful information on crop health, soil conditions, and resource needs. This enables farmers to apply pesticides, fertilizers, and irrigation with precision, improving crop yields and making the most use of available resources [44,45,46]. Computer-vision algorithms driven by AI provide automated crop management and monitoring. Drones and field-installed cameras may take pictures, and image-recognition algorithms can use those photos to find early indicators of weed infestations and nutritional deficits. This lessens the need for chemical treatments by empowering farmers to respond promptly, avoiding crop losses [23,24,47]. When paired with current agricultural and environmental data, AI models trained on previous data can reliably forecast crop yields [5]. AI systems are also able to recognize and categorize weeds, illnesses, and pests using visual cues and symptom assessments [6]. Deep-learning methods and computer-vision techniques are used by AI systems to identify possible crop dangers early on. This lessens the need for widespread pesticide applications by enabling farmers to implement focused preventative measures like localized interventions or precision spraying [8,12,48,49].

According to Soori et al. (2023) [2], artificial intelligence (AI)-driven irrigation systems improve water use by using sensor data. This increases total water-usage efficiency, encourages water conservation, and reduces water stress on plants [2]. Farm equipment is being revolutionized by AI technologies, which make automation and autonomous operations possible. AI-enabled robotic systems are very accurate and efficient in carrying out operations like planting, harvesting, and crop monitoring. This lowers the need for labor, boosts operational effectiveness, and raises total production [50].

Agricultural sustainability, which is the capacity to satisfy current demands without endangering those of future generations, has become a crucial issue. A radical transformation in agricultural techniques is required due to many factors, including the world’s population expansion, changing climate, depletion of natural resources, and the need for higher productivity [54]. Sustainable agriculture is sometimes defined as environmentally responsible methods that either improve environmental quality and the natural resource base that supports the agricultural economy or have little-to-no negative impact on natural ecosystems [32]. Generally, this is accomplished by safeguarding, reusing, replenishing, and preserving the foundation of natural resources, such as land (soil), water, and wildlife, which support the preservation of natural capital. Synthetic fertilizers are administered based on need, even though they may be used to augment natural inputs. Synthetic chemicals that are known to negatively impact biodiversity, soil structure, and organisms are either avoided entirely or used sparingly in sustainable agriculture [10].

In agricultural systems, sustainability encompasses the ideas of persistence—the ability of a system to endure over extended periods of time—and resilience—the ability of a system to withstand shocks and pressures. It also covers a wide range of broader economic, social, and environmental effects [35,71,72]. An alternative agricultural system known as “sustainable agriculture” has arisen to guarantee environmental sustainability while addressing the many challenges encountered by resource-poor farmers. It speaks to agriculture’s ability over time to improve the quality of the environment while also producing enough food and other commodities and services in ways that are lucrative, socially conscious, and efficient with the economy [11]. This system combines integrated methods of producing soil, crops, and animals with a reduction or elimination of external inputs that may be hazardous to consumers’ and farmers’ health as well as the environment. Rather, it places emphasis on the use of methods that include and are tailored to regional natural processes, such as biological nitrogen fixing, nutrient cycling, soil regeneration, and natural enemies of pests, into the processes involved in the production of food [71].

A farm has to be financially successful in order to be really sustainable. Alternative, more lucrative uses of the land replace farms that are not economically feasible. There are many ways that sustainable agriculture may increase a farm’s financial sustainability [19,73]. While better crop rotation and soil management can boost yields in the short term, other environmental benefits from sustainable practices, such as increased water availability and soil quality, can boost farm values over the medium and long terms and enable payments for environmental services [55]. Achieving economic viability might also include taking steps like cutting down on practices that could endanger the environment, the health of farmers, and the welfare of customers. Instead, farmers would depend on the particulars of the production system, the cost of the equipment, chemical fertilizer, and pesticides (for farmers who can afford these inputs) [22]. Of course, a variety of other elements, such as household qualities like managerial skill, institutions, infrastructure, and market access, among others, influence economic sustainability in addition to crop-production techniques [8,10,74,75].

The standard of living for both the people who live and work on the farm and the people in the neighboring villages is a key component of social sustainability. It entails making certain that various participants in the agricultural production chain get fair income or returns [15]. Since sustainable agriculture makes more use of available labor, at least for certain methods, it might encourage community members to share in the agricultural value generated in the setting of high unemployment. This promotes social fairness and cultural cohesiveness [5]. Despite the fact that the aforementioned components are often addressed individually, they are not incompatible: Sustainable agriculture concurrently achieves social, economic, and environmental goals. Sustainable agricultural techniques are often not novel; rather, they are based on long-standing knowledge and procedures, some of which have recently undergone favorable scientific evaluation [57,58].