Remote Sensing Application

The advancement of remote sensing provides a new opportunity for a data analytical platform for robust decision-making based on near real-time datasets derived from satellites and unmanned aerial vehicles (UAVs). The spectral signature through passive and active remote sensing has the advantages of providing information on plant responses in low-, medium-, and high-resolution images with temporal variability and enables taking action for sustainable agriculture and forest resource management. Therefore, the aim of this review article is to find a new avenue for generating data management platforms in the field of agriculture and forestry. The advancement of satellite remote sensing technology has already been suggested to open the gateway to establishing big data analytical platforms through decision support systems. Specifically, this review paper highlights some appropriate and important applications of satellite and UAV-derived indices and algorithms to address the scope and application of geographic information systems (GISs) in the field of agriculture and forestry research. The analytical signatures of changes in vegetation and water storage in leaves and water bodies were analyzed and presented using different phenological properties, land use land cover (LULC) changes, and natural disaster damage assessments to support policy formations and the livelihoods of farmers. The remote sensing and GIS-based analytical datasets cover crop calendars and phenological changes from forest canopies that refer to productivity according to seasons. Seasonal variations in the productivity of crops and forests can ensure appropriate actions with resilience for the sustainable management of bioresources.

Cereal-based food consumption and agricultural practices contribute to food nutritional insecurity, which has become a threatening issue in South Asian countries. The purpose of this research is to develop a seasonal land use planning model incorporating diversified crops for regional self-sufficiency based on land suitability and a balanced calorie demand. A multicriteria decision-making analysis was undertaken, and multicrop land planning maps were developed with the help of a geographical information system (GIS) and fuzzy membership functions. The vegetation index data were collected according to the crop calendar. The factors and constraints were generated in ArcGIS 10.4^® to perform spatial analysis. Fuzzy overlay analysis was performed to determine the suitable areas for crop production. The seasonal cropland suitability assessment results were validated with data from the Survey of Bangladesh (SoB). Among the three individual cropping seasons in Bangladesh, the analysis determined that, in the Kharif-1 season, 42% (3469 km²) of the total area was suitable for vegetable growing and, in the Kharif-2 season, the area of suitability was 55% (4543 km²). However, in the present practices, only 12% and 18% of the land are used for vegetable cultivation in the Kharif-1 and Kharif-2 seasons, respectively, which are less than the regional requirements. In addition, in the Rabi season, the most suitable zones for cereals, vegetables, pulses, oilseeds, and potatoes were reported as 35% (2891 km²), 19% (1569 km²), 15% (1239 km²), 10% (826 km²), and 21% (1734 km²) of the total land area, respectively. Moreover, the land areas suitable for farming pulses and oilseeds were found to be 15% (1239 km²) and 10% (826 km²), respectively. The integrated model proposed herein could be implemented for the management of land allocation for diversified crop production, providing more decision-making information for policymakers to ensure regional food nutrition security in the target area as well as in other South Asian countries.

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, LST, and 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 truth 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 = 0.773), ARVI (R² = 0.689), SARVI (R² = 0.711), MSAVI (R² = 0.745), and OSAVI (R² = 0.812) 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.

Sustainable land use is essential for increasing the production of cassava as a diversified crop for ensuring food security in Indonesia. Understanding the spatial factors and criteria is required for locating suitable production areas to increase cassava production. In this study, a spatial model was developed to assess the suitability of land for supporting sustainable cassava production. The model was divided into three stages considering different criteria. First, satellite digital images were processed from Landsat-4 Thematic Mapper (TM), Landsat-8 Operational Land Imager (OLI), and Sentinel-2 satellites to create vector data layers and a normalized difference vegetation index (NDVI) database. Second, a spatial analysis was performed to identify highly suitable areas for cassava production using a geographical information system (GIS) and the multi-criteria analysis including the analytical hierarchy process (AHP) and the analytical network process (ANP). Third, a sustainability evaluation was conducted based on land suitability information for a study period of 5 years. Land suitability assessment was performed to increase cassava production. We found that 43.11% (11,094 ha) of the study area was highly suitable for cassava production, whereas 30.87% (8233 ha) was moderately suitable and 9.83% (2623 ha) was marginally suitable with incorporating AHP analysis. Moreover, 17.69% (4718 ha) of the land was occupied by residents and settlements. On the other hand, ANP analysis also conducted to confirm the AHP results. Although many decision problems are studied through the AHP, however as the novelty in this study, ANP have added the better decision judgment based on the expert opinions. This research recommended that the integrated approach of GIS based on multi-criteria can be extended with satellite remote sensing vegetation datasets to assess the regional production and site-specific management of cassava crops.

The goal of this research was to collect visual information at the crop production that can be used for drought estimation. The study was completed to create an automated detection system of drought with high accuracy, low computing cost, and a lightweight deep learning model. Considering the advantages of YOLOv3, it was proposed to detect and localize vegetation phenology analysis under conditions of season in Indonesia. The study was planned to analyze the vegetation phenology to forecast drought during maize production at the central East Java areas of Indonesia. In the study, the vegetation index was utilized to produce the normalized difference vegetation index (NDVI) and normalized difference water index (NDWI) derived from Sentinel-2 to estimate water stress due to drought. According to the NDVI trajectory, the maize planting season was in April 2018, and the harvest was concluded in late August 2018. This study presents a convolutional neural network (CNN)-based you only look once (YOLO) model for detecting drought at the maize growth phases. The drought estimation was validated from the vegetation phenology analysis based on the growing season. The accuracy assessment of the deep learning model reported Intersection of Union (IoU) 83.4%, precision 98%, recall 99%, F1-Score 98%, and mean average precision 96% for the drought-prone areas. The deep learning analysis suggested that the proposed YOLOv3 model can perform robust and accurate detection of drought estimation from vegetation phenology.

Land suitability analysis is essential for a vineyard to increase its production and productivity under the dry conditions due to climate change. In this context, the purpose of this chapter is to determine the suitable locations for vineyards based on satellite remote sensing and GIS (geographical information system) to assess the suitability of land and least suitable land to support the vineyard growers for subsidy allocation. In this regard, the Landsat 8 operational land imager (OLI) and thermal infrared sensor (TIRS) and digital elevation (DM) shuttle radar topography mission (SRTM) images were processed to obtain the normalized difference vegetation index (NDVI), normalized difference moisture index (NDMI), land surface temperature (LST), and topographic maps (elevation, aspect, and slope). Moreover, JAXA rainfall information (mm per hour) and soil properties were used to incorporate climatic and soil conditions. Besides, socioeconomic information was collected through field surveys in Kabul Province in order to develop the vineyard suitability map. Finally, the suitable classes were determined using a weighted overly method based on the analytical hierarchy overlay process (AHP). The combined (physical and socioeconomic) suitability results indicated that highly suitable (12.9%), moderately suitable (25.5%), marginally suitable (28.5%), and not suitable lands (32.9%) were reported for grapes production in Kabul Province. The suitability models also indicated that 175.46 ha of vineyards out of 10599.96 ha of vineyards were located in marginal and not suitable areas. This research can support decision-makers, stakeholders, and growers with precise land assessments by identifying the main limiting criterion for producing table grape management. Furthermore, GIS analysis determined the vineyard growers from marginal and not suitable areas for providing support of subsidy to improve their livelihoods.

Land use changes significantly affect the sustainability of food security, ecological balance, and environmental protections in developing countries. Bangladesh is such a country that faces challenges from limited arable land resources, including the urbanization of agricultural lands and urban developments in suburban areas. Therefore, the aim of this chapter was to determine the land use changes over time in suburban areas that have potential for industrial growth. This chapter also assesses potential locations and the further growth of industries by land suitability analysis (LSA) to emphasize both agriculture and industries in terms of sustainable growth. A geographical information system (GIS)-based multi-criteria analysis (MCA) model was developed for the LSA to distinguish compact lands that were suitable for the economic zones of industries. Nine criteria, including seven constraints and 23 factors, are evaluated by the spatial analysis tools of ArcGIS^®. An analytical hierarchy process (AHP) was applied to prioritize the criteria based on experts’ opinions for the decision-making process of LSA. The study finds that densely located industrial areas have decreased agricultural lands by greater than 10% in the last two decades. Furthermore, the results of the LSA showed that only 4% of the lands were most suitable for industrial sites, whereas four compact lands had 16–10 ha of land, which was suitable for small industrial zones. Thus, the integrated GIS-MCA model could serve as a policy-planning tool to locate the economic zones of industries with sustaining agricultural lands and environmental protections.

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.

Indonesia has the highest forest density in the world, and the productivity of its forests can potentially be maximized to minimize CO₂ emissions. However, due to anthropogenic activities, phenological properties are subject to risk to ensure productivity and carbon exchange in the different forest ecosystems in Indonesia. Early prediction of carbon values could indicate a declining trend of forest quality with reference to vegetation levels. Thus, the purpose of this research is to evaluate forest productivity and carbon stock using phonological properties for different forests. The vegetation phenology was used to assess the level of forest productivity with different classifications to estimate carbon stock in six types of forest in south Sumatra using gross primary productivity (GPP) approaches. The vegetation phonologies were analyzed to develop a system dynamics model under two scenarios: first, a changing trend of normalized difference vegetation index (NDVI), and second, a changing trend of area, considering either increasing or decreasing solar radiation in both scenarios. This system was run through the geographic information system (GIS) environment to develop a database and to simulate results for future predictions. Verification was performed to test the simulation model by comparing the results with the Intergovernmental Panel on Climate Change (IPCC) reference. NDVI showed good correlations with GPP using MODIS MOD13Q1 for convertible production forest (CPF R² = 0.97), permanent production forest, PPF (R² = 0.99), limited production forest (LPF, R² = 0.98), tourism recreation forest (TRF, R² = 0.95), and wildlife reserve forest (WRF, R² = 0.95), nature reserve forest (NRF, R² = 0.99). The explicit differential function was used to estimate net primary productivity (NPP), which was related to the changes in area and productivity over time. Productivity and carbon stock analysis was performed via the proposal of five levels referring to Indonesian forest policy planning, considering resilience classified as high forest productivity (V1), moderate forest productivity (V2), marginal forest productivity (V3), very low forest productivity (N1), and no forest productive (N2). TRF was found to fall below the IPCC levels from 2015 to 2017, and NRF fall below the IPCC standards from 2015 to 2018. Therefore, the satellite-based remote sensing, system dynamics model can be implemented in the Indonesian forest policy system for assessing forest productivity and carbon stocks.

Despite recognizing the importance of tropical forest systems, deforestation in Malaysia has increased rapidly over the past 15 years. Since the first civilian earth observation satellite launched in 1972, remote sensing techniques and image processing analysis have been extensively used for long-term and continuous forest monitoring. This chapter selected the Google Earth Engine (GEE) platform to monitor deforestation in Malaysia from 2000 to 2020. GEE is a cloud-based platform that works with substantial geospatial datasets using high-performance computing resources. This chapter quantified trends of deforestation in Malaysia through the statistical approach based on GEE and used the quantitative data as a basis for analyzing the drivers of deforestation. The deforestation statistics for Malaysia from 2000 to 2020 was 86,893 km², with the highest deforestation in 2014. Overall, the statistical results demonstrated a high level of accuracy, and the GEE platform was confirmed to be suitable for forest monitoring on a national scale. Based on the statistical data of states in Malaysia, we further elaborated on the main drivers of deforestation. There is no single driver of tropical deforestation in Malaysia; the palm oil industry, forest fires, and illegal logging are attributed to the loss. The GEE monitoring tool was found appropriate for monitoring deforestation and has potential in guiding Malaysia’s management and conservation of forest resources.

The research project, “Climate-Resilient Agri-fisheries (CRA) Assessment, Targeting & Prioritization for the Adaptation and Mitigation Initiative in Agriculture (AMIA)” in Cordillera Administrative Region (CAR) contributes to the national government’s agenda of addressing climate change threats in the country’s agriculture sector. The major outputs include the Climate-Resilient Agri-fisheries (CRA) for the assessment of traditional and CRA cropping practices used by the farmers through cost-benefit analysis (CBA); and climate risk vulnerability assessment (CRVA) to determine the sensitivity and vulnerability assessment of crops of the province of Benguet. The CRVA assessment result showed that most of the municipalities in Benguet were classified as high to very high in terms of vulnerability to climate change based on their adaptive capacity, sensitivity of crops to the different climatic variables (temperature and precipitation) and hazards. Technologies identified for adaptation includes improving rainwater harvesting practice of the farmers to increase the yield and income of farmers especially during periods of drought and irregular rainfall. The use of blight-resistant variety Igorota (PO₃) can result in higher yield, cash returns, total returns, returns above cash costs, and returns above total costs. By planting PO₃, farmers significantly reduced their operational costs by about 50%. Effort is also thus needed to integrate the use of PO₃ with the water-saving practices to determine any synergies that could benefit the farmers in the vulnerable sites.

Sugarcane production data prior harvest are key information for optimizing harvest schedule and supply chain management, which contribute directly to the increase of profitability for both growers and sugar factories. Due to its flexibility, availability, and accessibility, unmanned aerial vehicle (UAV) imagery have been using to canopy detection, disease detection, sugar content estimation, and yield predictions of sugarcane. Vegetation index and machine learning technique were used to process images from multispectral camera and RGB camera and transformed into GIS data and validated with ground sampling data. Sugarcane canopy detection using linear discriminant analysis (LDA) obtained the highest accuracy of 97%. Normalized difference red edge index (NDREI) and green normalized difference vegetation index (GNDVI) yielded the highest potential for white-leaf disease detection for sugarcane. Chlorophyll Index-Red edge (ClRE) indicated good correlation with Brix of sugarcane around 0.90. Excess green (ExG) value was used to predict sugarcane yield with ordinary least square regression (OLSR) and obtained higher accuracy (R² = 0.75).

This chapter discusses the application of remote sensing perspective and how to develop the big data analytical platform for diversified land-use planning towards food and nutrition security, crop growth monitoring, yield forecasting, land suitability analysis, forest productivity and drought assessment for crops, vegetables, and fruits. The geospatial, mathematical, and logical modeling including multicriteria evaluation systems were conducted to determine the key outcomes of each chapter in this book have been lucidly discussed. Remote sensing and GIS-based systematic analysis are reported to indicate the biophysical and socioeconomic factors that bring sustainability in regional policy planning. The big data scheme for regional planning requires the high-density levels of data that ensures trustworthiness, authenticity, availability, and accountability of datasets. Furthermore, geospatial planning has the advantages of trustworthiness and authenticity in the intervention process to support the livelihoods of farmers during damages due to drought and flash floods. In regard to carbon stock analysis and forest loss assessment, ecological resource conservation is discussed referring to vegetation signatures derived from satellite imageries. Additionally, forest productivity assessment is explained based on carbon stock analysis to establish resilience in forest ecosystems.