Remote Sensing Applications in Agricultural, Earth and Environmental Sciences

1. Introduction

Remote sensing has become an essential tool in agricultural, earth and environmental sciences and offers significant insights into land use changes, climate variability, and resource management. The integration of satellite imagery, unmanned aerial systems (UASs), and machine learning techniques has enhanced the precision and effectiveness of monitoring in these fields [1]. With escalating concerns regarding climate change, land degradation, and food security, the capability to analyse large-scale spatial and temporal data has become increasingly pressing. This Editorial examines recent advancements in remote sensing applications, with an emphasis on the role of data fusion, AI-driven analysis, and cloud computing within these domains.

Increased satellite missions, including Moderate Resolution Imaging Spectroradiometer (MODIS), Sentinel, and Landsat, in conjunction with ground-based measurements, have facilitated high-resolution agricultural, earth and environmental assessments [2,3]. These datasets support a wide range of applications, from precision agriculture [4] and deforestation monitoring [5] to urban planning and hydrological modelling [6]. Advanced computational techniques, such as deep learning and object-based image analysis (OBIA), have improved model accuracy, which reinforces remote sensing as an essential resource for addressing global challenges in these fields [7]. Furthermore, cloud-based platforms such as Google Earth Engine (GEE) provide solutions for processing vast geospatial datasets and enhanced data accessibility for researchers worldwide [8].

With the rapid evolution of sensor technologies and computational methodologies, remote sensing continues to redefine monitoring and management in agricultural, earth and environmental sciences. The emergence of technologies such as hyperspectral imaging, Synthetic Aperture Radar (SAR), and edge computing is expected to refine geospatial analyses further and strengthen the role of remote sensing within these disciplines.

2. Overview of Published Articles

Recent studies illustrate the diverse applications of remote sensing across various scientific disciplines, including agricultural [4,9], earth [10] and environmental sciences [11]. Innovations in remotely sensed imagery, machine learning, and image processing techniques have significantly improved data accuracy and applicability, which support decision-making within these scientific sectors [1,12].

A key study investigated land cover changes by integrating the Land Use/Cover Area Frame Survey (LUCAS) database with Sentinel satellite imagery [13]. This research assessed the effectiveness of different classification techniques and offered a comparative analysis of their accuracy in distinguishing land cover types. The findings emphasised the importance of integrating large-scale datasets with high-resolution satellite imagery to enhance environmental monitoring and land use planning.

Similarly, advancements in climate data accuracy have been achieved by calibrating and validating MODIS-derived ground-level air temperature models. By incorporating extensive ground-based measurements, researchers refined these models and improved the reliability of climate trend analyses and forecasting.

Developments in image processing have further strengthened remote sensing applications [12]. A recent study introduced a fusion-based thresholding and non-linear diffusion approach to mitigate speckle noise in SAR imagery, enhancing data clarity and interpretability. These advancements are crucial for applications requiring high-precision remote sensing data, which may also include flood monitoring, disaster response, and infrastructure assessment.

In precision agriculture, remote sensing technologies have demonstrated their efficacy in optimising crop management [4,14]. One study examined the impact of nematode infestation on soybean production using aerial multispectral imagery and machine learning techniques. The findings highlighted the potential of artificial intelligence in identifying crop stress and facilitating targeted interventions to improve yield and mitigate economic losses.

Geological studies have also benefited from remote sensing advancements [15,16]. Machine learning algorithms were successfully applied to differentiate lithological formations in the Khyber Range and showcased the utility of remote sensing in geological mapping and mineral exploration. Furthermore, a combined approach integrating remote sensing data with ground-based observations enabled a spatio-temporal analysis of heatwaves, which provided insights into extreme temperature trends and their implications for climate adaptation strategies.

Vegetation monitoring has emerged as an important area where remote sensing is instrumental [17,18]. Automated computation of vine objects and ecosystem structures through UAS-based data acquisition and 3D point cloud analysis has demonstrated the effectiveness of object-based image analysis in ecological studies. Additionally, satellite-driven automation for detecting mowing events based on predicted compressed sward heights has enhanced grassland management, which contributes to sustainable pasture maintenance.

Climate studies have significantly advanced from remote sensing research [19]. A long-term analysis of mid-tropospheric temperature trends over Tibet and the Eastern Himalayas (1978–2022) utilised satellite-derived data to track atmospheric temperature changes. In a separate study, machine learning algorithms improved forest detection accuracy in southeastern Serbia, which enhanced land use monitoring and forest conservation. Moreover, multisource data fusion techniques facilitated historical eco-environmental quality mapping in China and highlighted the potential of remote sensing in large-scale ecological assessments.

Agricultural applications remain a focal point of remote sensing research [9,20]. Investigations into the predictive capabilities of single spectral bands, vegetation indices, and their combinations have provided valuable insights into nitrogen-level estimation in protected mountainous grasslands. Furthermore, unmanned aerial vehicle hyperspectral remote sensing has been utilised to detect ratholes in desert steppe regions. In contrast, hyperspectral imaging has been employed to analyse the influence of water availability on nitrogen discrimination in sugar beet and celery crops, which informs precision nutrient management strategies.

Urbanisation studies have also significantly benefited from remote sensing technologies, which aid in spatial planning and sustainable development [21,22]. Earth observation data have been utilised to assess and predict urban expansion patterns in Maseru, and the effectiveness of satellite imagery in guiding urban planning initiatives has been demonstrated. Additionally, soil properties and agricultural sustainability have been evaluated through the spatial modelling of agrochernozem properties, which support soil reclamation and sustainable land management. Statistical algorithms have further been applied to estimate multi-frequency, multi-polarisation backscattering coefficients over bare agricultural soils, which improve remote sensing applications in precision agriculture.

Emerging technologies continue to enhance the security and efficiency of remote sensing applications. A fog computing framework has been developed to detect energy-based attacks on UAV-assisted smart farming systems, which bridges the gap between cybersecurity and agricultural remote sensing [23]. Moreover, researchers have distinguished between human-induced and climate-driven land degradation in the Greater Sekhukhune District Municipality, which provides critical insights for land restoration and conservation efforts.

Hydrological and climatological studies increasingly rely on remote sensing for comprehensive environmental assessments [6]. A study employing multisource remotely sensed data and Google Earth Engine facilitated inter-seasonal estimations of grass water content indicators and offered valuable information for water resource management. An enhanced water quality index developed through remote sensing and machine learning has also introduced a novel approach to aquatic ecosystem monitoring. A comprehensive review of leaf area index estimation methods further highlights the significance of remote sensing in vegetation monitoring and sustainable land management.

Collectively, these studies emphasise the expanding capabilities of remote sensing in addressing contemporary challenges in agricultural, earth and environmental sciences. From precision agriculture and climate change analysis to urban planning and ecological assessments, advancements in remote sensing technologies continue to enhance our understanding of the environment and support sustainable development efforts across multiple disciplines.

3. Conclusions

The research presented in this Special Issue accentuates the growing significance of remote sensing in agricultural, earth and environmental sciences. Advances in artificial intelligence, satellite technology, and data fusion have substantially improved the accuracy and efficiency of environmental assessments, thus facilitating informed decision-making in land use planning, resource management, and climate adaptation.

Future remote sensing research should further explore the integration of machine learning, high-resolution imagery, and cloud-based analytics to address pressing agricultural, earth, and environmental challenges. By utilising these technological innovations, researchers can contribute to sustainable development and resilience against global changes in these fields. As the field progresses, interdisciplinary collaborations will be essential in maximising the potential of remote sensing for scientific discovery and policy implementation.