AI and Precision Agriculture doi: 10.3390/aipa1010003

Authors: Dimitrios Triantakonstantis Dionysios Faltsetas Despoina Vlachaki Ioannis Sebos Frank A. Coutelieris Nikos Koutsias

Soil variability within agricultural fields is rarely captured by conventional management, which applies inputs uniformly regardless of underlying spatial heterogeneity. This exploratory study evaluated whether freely available Sentinel-2 multispectral imagery, processed through Fuzzy C-Means (FCM) clustering in an open-source GIS environment, can support preliminary management-zone delineation in a small Mediterranean alfalfa field and whether targeted soil sampling can provide site-specific ground-truth evidence for the resulting zones. A Sentinel-2 Level-2A Bottom-of-Atmosphere (BOA) image acquired on 26 April 2022 from tile T34SDJ during peak alfalfa canopy development was used to calculate four spectral indices: Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI), Enhanced Vegetation Index (EVI), and Normalized Difference Water Index (NDWI). These indices were standardized prior to clustering and synthesized through FCM to delineate management zones within a field of 8 ha in Etoloakarnania, western Greece. Six georeferenced composite soil samples were then collected from locations within the mapped zones to provide preliminary validation of the spectral zones. The two zones showed strong directional differences in several soil fertility indicators. Available phosphorus differed by a factor of 6.5 between zones (62.0 vs. 9.45 mg kg−1), with a localized high-value point reaching 110 mg kg−1 within the higher-fertility zone. Exchangeable potassium followed the same pattern (0.71 vs. 0.28 meq 100 g−1). DTPA-extractable iron differed three-fold (112.0 vs. 37.37 mg kg−1) and zinc nearly five-fold (2.79 vs. 0.56 mg kg−1), while pH was virtually identical across zones (6.15–6.20). These results suggest that, in this site-specific case, the combination of Sentinel-2 indices and FCM clustering produced spatial zones that were broadly consistent with measured soil-fertility contrasts. However, because the validation dataset consisted of only six composite soil samples and because sample-level FCM membership scores, spectral-index values, and formal cluster-validity diagnostics were not retained from the original workflow, the findings should be interpreted as an exploratory screening exercise rather than as a validated decision-support tool. Further soil sampling, yield or biomass monitoring, multi-season assessment, formal cluster diagnostics, and local fertilizer-threshold evaluation are required before operational nutrient prescriptions are implemented.

AI and Precision Agriculture doi: 10.3390/aipa1010002

Authors: Nikolaos Giakoumoglou Dimitrios Kapetas Kleanthis Marios Papadopoulos Panagiotis Christakakis Tania Stathaki Eleftheria Maria Pechlivani

Artificial intelligence (AI) has emerged as a transformative tool for plant health monitoring, offering new opportunities for scalable, timely, and data-driven pest and disease management in agriculture. This review provides a comprehensive synthesis of AI-based methods for pest and plant disease detection, systematically organizing existing literature across sensing modalities, learning paradigms, and deployment scales. We distinguish between population-level pest monitoring, plant-centric visual inspection, and field-scale surveillance, as well as between post-symptomatic disease recognition and pre-symptomatic detection enabled by spectral imaging technologies. Beyond summarizing recent advances, this work places strong emphasis on critical analysis, discussing fundamental limitations related to data scarcity, domain shift, generalization under field conditions, and the challenge of disentangling biotic from abiotic stress factors. The review further examines the distinction between correlation-driven AI predictions and causal disease understanding, positioning AI as a complementary decision-support tool alongside established diagnostic methods. Building on these insights, we outline key future research directions, including multimodal sensor fusion, explainable and trustworthy AI, edge-based deployment for real-time monitoring, and the development of foundation models for unified agricultural intelligence. This review aims to serve as both an accessible entry point and a critical reference for advancing AI-driven plant health management.

AI and Precision Agriculture doi: 10.3390/aipa1010001

Authors: De Liu

Global food systems are under increasing pressure due to population growth, with food demand projected to rise substantially by the mid-century [...]