Satellite remote sensing technologies have a high potential in applications for evaluating land conditions and can facilitate optimized planning for agricultural sectors. However, misinformed land selection decisions limit crop yields and increase production-related costs to farmers. Therefore, the purpose of this research was to develop a land suitability assessment system using satellite remote sensing-derived soil-vegetation indicators. A multicriteria decision analysis was conducted by integrating weighted linear combinations and fuzzy multicriteria analyses in a GIS platform for suitability assessment using the following eight criteria: elevation, slope, and LST vegetation indices (SAVI, ARVI, SARVI, MSAVI, and OSAVI). The relative priorities of the indicators were identified using a fuzzy expert system. Furthermore, the results of the land suitability assessment were evaluated by ground truthed yield data. In addition, a yield estimation method was developed using indices representing influential factors. The analysis utilizing equal weights showed that 43% of the land (1832 km²) was highly suitable, 41% of the land (1747 km²) was moderately suitable, and 10% of the land (426 km²) was marginally suitable for improved yield productions. Alternatively, expert knowledge was also considered, along with references, when using the fuzzy membership function; as a result, 48% of the land (2045 km²) was identified as being highly suitable; 39% of the land (2045 km²) was identified as being moderately suitable, and 7% of the land (298 km²) was identified as being marginally suitable. Additionally, 6% (256 km²) of the land was described as not suitable by both methods. Moreover, the yield estimation using SAVI (R² = 77.3%), ARVI (R² = 68.9%), SARVI (R² = 71.1%), MSAVI (R² = 74.5%) and OSAVI (R² = 81.2%) showed a good predictive ability. Furthermore, the combined model using these five indices reported the highest accuracy (R² = 0.839); this model was then applied to develop yield prediction maps for the corresponding years (2017–2020). This research suggests that satellite remote sensing methods in GIS platforms are an effective and convenient way for agricultural land-use planners and land policy makers to select suitable cultivable land areas with potential for increased agricultural production.

In an orchard automation process, a current challenge is to recognize natural landmarks and tree trunks to localize intelligent robots. To overcome low-light conditions and global navigation satellite system (GNSS) signal interruptions under a dense canopy, a thermal camera may be used to recognize tree trunks using a deep learning system. Therefore, the objective of this study was to use a thermal camera to detect tree trunks at different times of the day under low-light conditions using deep learning to allow robots to navigate. Thermal images were collected from the dense canopies of two types of orchards (conventional and joint training systems) under high-light (12–2 PM), low-light (5–6 PM), and no-light (7–8 PM) conditions in August and September 2021 (summertime) in Japan. The detection accuracy for a tree trunk was confirmed by the thermal camera, which observed an average error of 0.16 m for 5 m, 0.24 m for 15 m, and 0.3 m for 20 m distances under high-, low-, and no-light conditions, respectively, in different orientations of the thermal camera. Thermal imagery datasets were augmented to train, validate, and test using the Faster R-CNN deep learning model to detect tree trunks. A total of 12,876 images were used to train the model, 2318 images were used to validate the training process, and 1288 images were used to test the model. The mAP of the model was 0.8529 for validation and 0.8378 for the testing process. The average object detection time was 83 ms for images and 90 ms for videos with the thermal camera set at 11 FPS. The model was compared with the YOLO v3 with same number of datasets and training conditions. In the comparisons, Faster R-CNN achieved a higher accuracy than YOLO v3 in tree truck detection using the thermal camera. Therefore, the results showed that Faster R-CNN can be used to recognize objects using thermal images to enable robot navigation in orchards under different lighting conditions.

Land evaluation is important for assessing environmental limitations that inhibit higher yield and productivity in tea. The aim of this research was to determine the suitable lands for sustainable tea production in the northeastern part of Bangladesh using phenological datasets from remote sensing, geospatial datasets of soil–plant biophysical properties, and expert opinions. Sentinel-2 satellite images were processed to obtain layers for land use and land cover (LULC) as well as the normalized difference vegetation index (NDVI). Data from the Shuttle Radar Topography Mission (SRTM) were used to generate the elevation layer. Other vector and raster layers of edaphic, climatic parameters, and vegetation indices were processed in ArcGIS 10.7.1^® software. Finally, suitability classes were determined using weighted overlay of spatial analysis based on reclassified raster layers of all parameters along with the results from multicriteria analysis. The results of the study showed that only 41,460 hectares of land (3.37% of the total land) were in the highly suitable category. The proportions of moderately suitable, marginally suitable, and not suitable land categories for tea cultivation in the Sylhet Division were 9.01%, 49.87%, and 37.75%, respectively. Thirty-one tea estates were located in highly suitable areas, 79 in moderately suitable areas, 24 in marginally suitable areas, and only one in a not suitable area. Yield estimation was performed with the NDVI (R² = 0.69, 0.66, and 0.67) and the LAI (R² = 0.68, 0.65, and 0.63) for 2017, 2018, and 2019, respectively. This research suggests that satellite remote sensing and GIS application with the analytical hierarchy process (AHP) could be used by agricultural land use planners and land policy makers to select suitable lands for increasing tea production.

Drought is one of the detrimental climatic factors that affects the productivity and quality of tea by limiting the growth and development of the plants. The aim of this research was to determine drought stress in tea estates using a remote sensing technique with the standardized precipitation index (SPI). Landsat 8 OLI/TIRS images were processed to measure the land surface temperature (LST) and soil moisture index (SMI). Maps for the normalized difference moisture index (NDMI), normalized difference vegetation index (NDVI), and leaf area index (LAI), as well as yield maps, were developed from Sentinel-2 satellite images. The drought frequency was calculated from the classification of droughts utilizing the SPI. The results of this study show that the drought frequency for the Sylhet station was 38.46% for near-normal, 35.90% for normal, and 25.64% for moderately dry months. In contrast, the Sreemangal station demonstrated frequencies of 28.21%, 41.02%, and 30.77% for near-normal, normal, and moderately dry months, respectively. The correlation coefficients between the SMI and NDMI were 0.84, 0.77, and 0.79 for the drought periods of 2018–2019, 2019–2020 and 2020–2021, respectively, indicating a strong relationship between soil and plant canopy moisture. The results of yield prediction with respect to drought stress in tea estates demonstrate that 61%, 60%, and 60% of estates in the study area had lower yields than the actual yield during the drought period, which accounted for 7.72%, 11.92%, and 12.52% yield losses in 2018, 2019, and 2020, respectively. This research suggests that satellite remote sensing with the SPI could be a valuable tool for land use planners, policy makers, and scientists to measure drought stress in tea estates.

Unmanned aerial vehicle (UAV)-based spraying systems have recently become important for the precision application of pesticides, using machine learning approaches. Therefore, the objective of this research was to develop a machine learning system that has the advantages of high computational speed and good accuracy for recognizing spray and non-spray areas for UAV-based sprayers. A machine learning system was developed by using the mutual subspace method (MSM) for images collected from a UAV. Two target lands: agricultural croplands and orchard areas, were considered in building two classifiers for distinguishing spray and non-spray areas. The field experiments were conducted in target areas to train and test the system by using a commercial UAV (DJI Phantom 3 Pro) with an onboard 4K camera. The images were collected from low (5 m) and high (15 m) altitudes for croplands and orchards, respectively. The recognition system was divided into offline and online systems. In the offline recognition system, 74.4% accuracy was obtained for the classifiers in recognizing spray and non-spray areas for croplands. In the case of orchards, the average classifier recognition accuracy of spray and non-spray areas was 77%. On the other hand, the online recognition system performance had an average accuracy of 65.1% for croplands, and 75.1% for orchards. The computational time for the online recognition system was minimal, with an average of 0.0031 s for classifier recognition. The developed machine learning system had an average recognition accuracy of 70%, which can be implemented in an autonomous UAV spray system for recognizing spray and non-spray areas for real-time applications.

The objective of this research was to detect changes in forest areas and, subsequently, the potential forest area that can be extended in the South Sumatra province of Indonesia, according to the Indonesian forest resilience classification zones. At first, multispectral satellite remote sensing datasets from Landsat 7 ETM+ and Landsat 8 OLI were classified into four classes, namely urban, vegetation, forest and waterbody to develop Land Use/Land Cover (LULC) maps for the year 2003 and 2018. Secondly, criteria, namely distance from rivers, distance from roads, elevation, LULC and settlements were selected and the reclassified maps were produced from each of the criteria for the land suitability analysis for forest extension. Thirdly, the Analytical Hierarchy Process (AHP) was incorporated to add expert opinions to prioritize the criteria referring to potential areas for forest extension. In the change detection analysis, Tourism Recreation Forest (TRF), Convertible Protection Forest (CPF) and Permanent Production Forest (PPF) forest zones had a decrease of 20%, 13% and 40% in area, respectively, in the forest class from 2003 to 2018. The Limited Production Forest (LPF) zone had large changes and decreased by 72% according to the LULC map. In the AHP method, the influential criteria had higher weights and ranked as settlements, elevation, distance from roads and distance from rivers. CPF, PPF and LPF have an opportunity for extension in the highly suitable classification (30%) and moderately suitable classification (41%) areas, to increase coverage of production forests. Wildlife Reserve Forests (WRFs) have potential for expansion in the highly suitable classification (30%) and moderately suitable classification (52%) areas, to keep biodiversity and ecosystems for wildlife resources. Nature Reserve Forests (NRFs) have an opportunity for extension in the highly suitable classification (39%) and moderately suitable classification (48%) areas, to keep the forests for nature and biodiversity. In case of TRF, there is limited scope to propose a further extension and is required to be managed with collaboration between the government and the community.