Heterogeneous Agricultural Areas Research Articles

Assessment of the impact of land cover changes on sediment yield: a case study

Abstract Land use is one of the most important variables impacting river basin water and land resource planning and management. Sediment transport in streams is an important issue in the assessment of sediment deposition in dam reservoirs and its impact on operational activities. Evaluation of sediment yield contributes to decision-makers for effective water management and protection of the dam body and its elements. In this study, land use cover changes, in particular in forest areas, agricultural areas, arable lands, permanent crops, heterogeneous agricultural areas, and pastures in the Çakıt and Körkün sub-basins of the Seyhan River basin were examined between 1990 and 2018 using CORINE land use cover (CLC) data. The effect of land use/land cover (LULC) modifications on sediment yield was studied using suspended sediment observation data and CLC data. It was determined that the forest area in the Çakıt sub-basin drainage area increased between 1990 and 2018, and decreased in the Körkün sub-basin. It was determined that the increase in forest area in the Çakıt sub-basin drainage region until 2018 helped to reduce sediment movement. The regression values between forest area and suspended sediment concentration in Çakıt and Körkün sub-basins were found to be 0.9521 and 0.4431, respectively.

Spatio-temporal investigation of urbanization and its impact on habitat fragmentation in natural ecosystems of Istanbul using Shannon’s entropy and landscape metrics in GIS

AbstractThis study aims to investigate the impact of spatio-temporal dynamics of urban sprawl on habitats in Istanbul, using the CORINE 1990 and 2018 land cover datasets. In this context, by means of geographic information system (GIS) tools and techniques, land cover maps are created for land cover change analysis and visualization, the Shannon’s entropy method is performed for measuring urban growth and sprawl, and the landscape metrics method is applied for assessing habitat loss and fragmentation. Results indicate that the rate of urban sprawl in the area increased by 0.1230 as per the Shannon’s entropy index over the 28-year period. Similarly, the Shannon Diversity Index and the Shannon Evenness Index rose from 1.74 to 1.85 and from 0.68 to 0.70, respectively, indicating an increase in urbanization within the area. Moreover, an analysis of patch numbers reveals that habitat fragmentation increased in shrub and/or herbaceous vegetation associations (72.55%), heterogeneous agricultural areas (45.11%), arable lands (42.5%), forests (36.13%) and pastures (15.05%), due to urbanization. Habitat fragmentation has had a detrimental effect on the local biodiversity. While 15 flora species were identified as vulnerable, 13 as endangered and 9 as critically endangered, 19 fauna species were identified as vulnerable and 5 as endangered. This study highlights that the natural habitats and biodiversity of Istanbul will suffer further decline due to urbanization unless sustainable urban planning and management policies are put into practice. It is essential to have controlled urban development to preserve the ecosystem’s carrying capacity, and urbanization decisions must consider this requirement.

Geospatial prediction of total soil carbon in European agricultural land based on deep learning

Accurate geospatial prediction of soil parameters provides a basis for large-scale digital soil mapping, making efficient use of the expensive and time-consuming process of field soil sampling. To date, few studies have used deep learning for geospatial prediction of soil parameters, but there is evidence that it may provide higher accuracy compared to machine learning methods. To address this research gap, this study proposed a deep neural network (DNN) for geospatial prediction of total soil carbon (TC) in European agricultural land and compared it with the eight most commonly used machine learning methods based on studies indexed in the Web of Science Core Collection. A total of 6209 preprocessed soil samples from the Geochemical mapping of agricultural and grazing land soil (GEMAS) dataset in heterogeneous agricultural areas covering 4,899,602 km2 in Europe were used. Prediction was performed based on 96 environmental covariates from climate and remote sensing sources, with extensive comprehensive hyperparameter tuning for all evaluated methods. DNN outperformed all evaluated machine learning methods (R2 = 0.663, RMSE = 9.595, MAE = 5.565), followed by Quantile Random Forest (QRF) (R2 = 0.635, RMSE = 25.993, MAE = 22.081). The ability of DNN to accurately predict small TC values and thus produce relatively low absolute residuals was a major reason for the higher prediction accuracy compared to machine learning methods. Climate parameters were the main factors in the achieved prediction accuracy, with 23 of the 25 environmental covariates with the highest variable importance being climate or land surface temperature parameters. These results demonstrate the superiority of DNN over machine learning methods for TC prediction, while highlighting the need for more recent soil sampling to assess the impact of climate change on TC content in European agricultural land.

Spatial variation of agricultural land in Turkey using CORINE data

Detection of the exchange and distribution of agricultural lands allows many projects and plans to be made and interpreted correctly, such as food safety, planning, and environmental risk analysis. From this point of study in the spatial changes and distribution of agricultural land in time across Turkey were examined. CORINE Land Cover (CLC) data was used to identify agricultural land and examine changes over time. As a result of the study, it was observed that agricultural lands increased slightly from 1990 to 2018, but this increase has not always been in the form of preserving existing agricultural lands and adding existing agricultural lands. While some areas have lost their agricultural land characteristics, some areas have become agricultural land. New agricultural areas are usually realized by the transformation of forests and semi-natural areas while the agricultural areas that disappear are provided from heterogeneous agricultural areas. The Central Anatolia region stands out in the distribution of agricultural areas by region. The region with the highest concentration of agricultural land in terms of both proportion and area is the Central Anatolia region. Also, the Central Anatolia region is the region with the most intensive Non-irrigated agriculture. The area where irrigated agriculture is proportionally most made is the southeast Anatolia region. According to province-based, the provinces with more than 40% of the provincial surface area are Kırıkkale, Kırşehir, Nevşehir, Aksaray in the Central Anatolia region, Gaziantep and Şanlıurfa in the Southeastern Anatolia region, Edirne and Tekirdağ in the Marmara region. The provinces of Artvin, Tunceli, Bingöl, and Hakkari are the provinces where the percentage of agricultural land is below 10%.

Land Cover Classification in the Antioquia Region of the Tropical Andes Using NICFI Satellite Data Program Imagery and Semantic Segmentation Techniques

Land cover classification, generated from satellite imagery through semantic segmentation, has become fundamental for monitoring land use and land cover change (LULCC). The tropical Andes territory provides opportunities due to its significance in the provision of ecosystem services. However, the lack of reliable data for this region, coupled with challenges arising from its mountainous topography and diverse ecosystems, hinders the description of its coverage. Therefore, this research proposes the Tropical Andes Land Cover Dataset (TALANDCOVER). It is constructed from three sample strategies: aleatory, minimum 50%, and 70% of representation per class, which address imbalanced geographic data. Additionally, the U-Net deep learning model is applied for enhanced and tailored classification of land covers. Using high-resolution data from the NICFI program, our analysis focuses on the Department of Antioquia in Colombia. The TALANDCOVER dataset, presented in TIF format, comprises multiband R-G-B-NIR images paired with six labels (dense forest, grasslands, heterogeneous agricultural areas, bodies of water, built-up areas, and bare-degraded lands) with an estimated 0.76 F1 score compared to ground truth data by expert knowledge and surpassing the precision of existing global cover maps for the study area. To the best of our knowledge, this work is a pioneer in its release of open-source data for segmenting coverages with pixel-wise labeled NICFI imagery at a 4.77 m resolution. The experiments carried out with the application of the sample strategies and models show F1 score values of 0.70, 0.72, and 0.74 for aleatory, balanced 50%, and balanced 70%, respectively, over the expert segmented sample (ground truth), which suggests that the personalized application of our deep learning model, together with the TALANDCOVER dataset offers different possibilities that facilitate the training of deep architectures for the classification of large-scale covers in complex areas, such as the tropical Andes. This advance has significant potential for decision making, emphasizing sustainable land use and the conservation of natural resources.

Quantification of the spatial resilience of the Spanish rural landscape to fire occurrence analysed using the SISPARES network of plots

ContextIn Spain, fire is a tool used for management in rural landscapes but also wildfires can play a disruptive socio-ecological role. Therefore, its spatial structure analysis and spatial resilience quantification to wildfire is useful for territorial planning and management.ObjectivesWe evaluate the relationship between the spatial structure of Spanish rural landscapes with the historical wildfire frequency. We develop and calculate indices of spatial resilience to wildfires and large wildfires.MethodsWe followed a stratified sampling based on the biogeoclimatic classes grouping by ecoregions. We calculated landscape metrics with Fragstats and collected wildfires occurrence from a national wildfire database. Spatial resilience was estimated with a self-elaborated index, using wildfires data and landscape structure subjected to a MANOVA and to a linear regression model.ResultsThe Northwest region suffered more wildfires and large wildfires than the other ecoregions. The differences in frequency of large wildfires were small and low in. Some landscape metrics were positively related to wildfire frequency (forest plantations and scrublands) and other negatively (“dehesas” and crops). Spatial resilience to wildfires and large wildfires was lower in the Northwest area but for large wildfires were also low in the Mediterranean Littoral and Central region.ConclusionsThe relationship between the frequency of the two types of wildfires and landscape structure determines differences in spatial resilience indices. Large wildfires are positively related to shrubland abundance, whereas small wildfires are positively related to heterogeneous agricultural areas. Therefore, spatial resilience indices could be used as early warning tools to prevent wildfires.

Implications of future land-use/cover pattern change on landslide susceptibility at a national level: A scenario-based analysis in Romania

Land-use/cover (LUC) change is a global change forcing with important impacts on landslides, which highlights the need to evaluate the potential future evolution of these hazards under future LUC scenarios. Accordingly, the current paper provides a first national-level exploration on the possible effects of LUC pattern change on landslide susceptibility (LS) in Romania, shedding light on the evolution of one of Europe’s landslide hotspot countries as well as one of the territories significantly affected by recent LUC change, especially after the fall of the communist regime. Two countrywide future LS maps were modelled for 2075, by applying a previously developed national scale-adapted LS empirical procedure, integrating therein two existing long-term LUC pattern forecasts and assuming no change for the other landslide controlling factors. The estimated future LS maps were then compared to the current LS zonation using a pixel-based analysis to estimate the contribution of LUC class transitions to the LS variation in time. The quantitative examination of LS changes suggests an overall net slight decrease at the national level under both scenarios (on an average of 7.3% of the LUC change area), with more significant regional variations. The location and extent of the estimated potential LUC transitions reflect themselves into a clear influence on the future LS level manifesting itself, on average, over 7.1% of the country’s area. The analysis demonstrates that the expected increase in the forest-covered area brings the most important contribution to the decrease of the LS level. An average of 44.2% of the total LS decrease area was mainly predicted by the transitions from pastures and natural grasslands/scrubs to forests, and 11.4% by that from heterogeneous agricultural areas to forests. Conversely, transitions to pastures and natural grasslands resulted in the most important contribution to the increase of the LS level (52.2%). Transitions among other agricultural lands resulted in slight susceptibility variations or in no change. Through the analysed LUC scenarios, differing in terms of the implementation of environmental management regulations inside protected areas, the study proves that a more appropriate land management could have an important influence on decreasing LS, a finding of particular relevance for encouraging and extending a conscious application of protective land measures, especially on slopes which are degraded or prone to instability, in a country otherwise characterised by an overall relative implementation of environmental policies. In addition, the analysis reveals that a significant proportion (24.2%) of the projected new built-up areas is expected to spread by 2075 over lands with moderate, high and very high LS, resulting in potentially new landslide exposure hotspots in the future in both rural and urban areas. The obtained results could be used in directing landslide risk reduction actions and decisions primarily towards the management of LUC and towards prioritizing areas for such measures, while, from a theoretical perspective, this approach could be extended to future investigations related to LUC change implications for landslide hazard and risk in Romania, but could also be followed in case of other national territories.

Zoning of Potential Areas for the Production of Oleaginous Species in Colombia under Agroforestry Systems

Due to the need to develop more agroforestry systems, the Moringa oleifera, Olea Europea, Glycine max, Brassica napus, Helianthus annuus, and Jatropha curcas are identified as unconventional species for their expansion under these systems in Colombia. With the Colombian Environmental Information System (SIAC) database, zoning was carried out according to the agroclimatic species requirements and optimal coverage for their production. As a result, a total area of 212,977.2 km2 was identified, mainly including the departments of Casanare, Arauca, Vichada, Guajira, Córdoba, Meta, Magdalena, Cesar, Tolima, and Cundinamarca. The species and associations species with the most options for productive expansion are Moringa (75,758 km2), Moringa, Jatropha, and Sunflower (42,515.1 km2), Moringa and Jatropha (37,180.4 km2), Jatropha (20,840 km2), Jatropha and Sunflower (17,692.1 km2), Olive (7332.1 km2), and Soybean (3586.3 km2). Of the potential agroforestry areas to their establishment, 36% correspond to herbaceous and/or shrubby vegetation, 34% to grasses, and 22% to heterogeneous agricultural areas. This research is the first step to representing the agronomic versatility of these promising species and their potential contribution to the diversification of the agri-food and agroforestry sectors.

Land use classification over smallholding areas in the European Common Agricultural Policy framework

Land use (LU) monitoring and mapping from remote sensing (RS) data are relevant topics in Earth observation (EO). LU monitoring requires powerful/robust classification approaches able to provide reliable identifications in decision-making applications, even over challenging areas. The European Common Agricultural Policy (CAP) promotes the use of remote sensing for LU monitoring in Europe useful in the compliance control of the subsidy payments. In this context, the present study proposes a novel classification chain to identify ten land uses, namely: forest (FOR), pasture with trees (TRE), pasture with shrubs (SHR), pastureland (PAS), vineyard (VIN), arable land (ARL), fruit trees (FRU), nut trees (NUT), citrus (CIT), and olive grove (OLI), over three areas in the Valencian Autonomous Region (Spain) where smallholding farming predominates. The approach exploits the multitemporal information provided by Sentinel-2 data using a novel spatial strategy specifically designed to deal with heterogeneous agricultural areas. More precisely, we implemented a deep learning algorithm based on bidirectional recurrent neural networks to account for complex temporal dynamics. The classification results over the three areas showed accuracies higher than 95.5% over validation sets composed of in-situ checks never used during the training process. The proposed methodology outperformed standard approaches that not consider the spatial variability of the training samples, and revealed very good agreement concerning the Land Parcel Identification System (LPIS) of Spain. In addition, the developed chain proposes the novelty of using the kernel normalized difference vegetation index (kNDVI) as a predictor in a LU classification processing chain. Including the kNDVI instead of the traditional NDVI outperformed the classification accuracy in all metrics and classes. Ultimately, the obtained classifications were used for assessing the 2020 farmers’ declarations in the three study areas. The declarations showed a level of agreement concerning the proposed approach near 99%.

A robust index to extract paddy fields in cloudy regions from SAR time series

Timely and accurate mapping of paddy rice cultivation is needed for maintaining sustainable rice production, ensuring food security, and monitoring water usage. Synthetic Aperture Radar (SAR) remote sensing plays an important role in the continuous monitoring and mapping of rice cultivation in cloudy regions since it is not affected by weather conditions. To date, most SAR imagery-based rice mapping methods rely on prior knowledge (e.g., the planting date) and empirical thresholds for specific regions, which limits their applications in large spatial scales. To tackle this limitation, this study proposed a new SAR-based Paddy Rice Index (SPRI) to quantify the probability of land patches planted paddy rice. SPRI fully uses unique features of paddy rice during the transplanting-vegetative period in the Sentinel-1 VH backscatter time series. With the assistance of cloud-free Sentinel-2 images, SPRI can be calculated for each cropland object with adaptive parameters. Then, SPRI values of cropland objects can be converted to paddy rice maps using the binary-classification threshold. The proposed SPRI method was tested at five sites with diverse climate conditions, landscape complexity and cropping systems. Results show that the SPRI was able to produce an accurate classification map with an overall accuracy of over 88% and an F1 score of over 0.86 at all sites. Compared with the existing SAR-based rice mapping methods, our method performed much better in heterogeneous agricultural areas where rice is mosaiced with other crops. As SPRI does not need any prior knowledge, reference samples and many predefined parameters, it has high flexibility and applicability to support paddy rice mapping in large areas, especially for cloudy regions where optical remote sensing data is often not available.

Temporal Sequence Object-based CNN (TS-OCNN) for crop classification from fine resolution remote sensing image time-series

Accurate crop distribution mapping is required for crop yield prediction and field management. Due to rapid progress in remote sensing technology, fine spatial resolution (FSR) remotely sensed imagery now offers great opportunities for mapping crop types in great detail. However, within-class variance can hamper attempts to discriminate crop classes at fine resolutions. Multi-temporal FSR remotely sensed imagery provides a means of increasing crop classification from FSR imagery, although current methods do not exploit the available information fully. In this research, a novel Temporal Sequence Object-based Convolutional Neural Network (TS-OCNN) was proposed to classify agricultural crop type from FSR image time-series. An object-based CNN (OCNN) model was adopted in the TS-OCNN to classify images at the object level (i.e., segmented objects or crop parcels), thus, maintaining the precise boundary information of crop parcels. The combination of image time-series was first utilized as the input to the OCNN model to produce an ‘original’ or baseline classification. Then the single-date images were fed automatically into the deep learning model scene-by-scene in order of image acquisition date to increase successively the crop classification accuracy. By doing so, the joint information in the FSR multi-temporal observations and the unique individual information from the single-date images were exploited comprehensively for crop classification. The effectiveness of the proposed approach was investigated using multitemporal SAR and optical imagery, respectively, over two heterogeneous agricultural areas. The experimental results demonstrated that the newly proposed TS-OCNN approach consistently increased crop classification accuracy, and achieved the greatest accuracies (82.68% and 87.40%) in comparison with state-of-the-art benchmark methods, including the object-based CNN (OCNN) (81.63% and 85.88%), object-based image analysis (OBIA) (78.21% and 84.83%), and standard pixel-wise CNN (79.18% and 82.90%). The proposed approach is the first known attempt to explore simultaneously the joint information from image time-series with the unique information from single-date images for crop classification using a deep learning framework. The TS-OCNN, therefore, represents a new approach for agricultural landscape classification from multi-temporal FSR imagery. Besides, it is readily generalizable to other landscapes (e.g., forest landscapes), with a wide application prospect.

Land cover changes in coffee cultural landscapes of Pereira (Colombia) between 1997 and 2014

Understanding how and what land cover changes and transitions have occurred in a territory is crucial to planning and managing high-demand surfaces. At the landscape level, the challenge is determining the allocation and management of various land cover options. Therefore, for natural resources planning and management, a study characterizing and analysing the territory of interest should be included. This work aimed to analyse the changes and land cover patterns in the city of Pereira, Colombia, within the framework of the Colombian Coffee Cultural Landscape. The evaluated period was between 1997 and 2014, and a Geographic Information System, ENVI 4.8 programme and QGIS programme were used for multitemporal analysis. To describe the land cover transitions, two temporal moments were analysed with Landsat satellite images: one moment was for the year 1997, which was taken in August (Landsat 5), and the other moment was for the year 2014, which was taken in July (Landsat 8). At level 1 of CORINE (Coordination of information on the environment), the areas of land cover corresponding to agricultural areas, forests and semi-natural areas decreased most in the analysis period, while artificial surfaces increased. At level 3, the cover with the greatest decrease in territory was coffee crops, which showed a negative annual loss rate of -3.97%, followed by permanent crops (-2.67%). The continuous and discontinuous urban fabric showed the greatest growth with a positive annual rate of 4.14%. In conclusion, the land cover that lost the most territory was coffee crop, mainly due to political-economic factors, such as the dissolution of the International Coffee Agreement and the National Federation of Coffee Growers that discouraged coffee cultivation and permanent crops. Likewise, sociocultural factors, such as smallholder farmers have guided the changes in land cover and have stimulated productive styles to adapt and remain, increasing heterogeneous agricultural areas.

Individual Movements and Habitat Use in Temporary Settlement Areas, Wintering Grounds and Breeding Areas of Saker Falcons Falco cherrug in the Pannonian Basin

Understanding the year-round movement behaviour is fundamental for the effective conservation management of an ecologically important species. In the heavily human-modified landscape of Central Europe, Saker Falcons Falco cherrug have adapted to intensively managed agricultural habitats, often nesting and roosting on electrical pylons. We studied the ranging behaviour and habitat selection of one juvenile and three adult Saker Falcons equipped with GPS/GSM loggers in the Czech Republic and Austria between 2015–2017. Upon release from a rescue centre, the juvenile Saker Falcon used temporary settlement areas (TSAs) with a median size of 231 km2 (minimum convex polygons, MCP 95%). Median of breeding season home ranges for the three adults was 15 km2 over six breeding events. After breeding period, the adults remained close to the nest site, occupying an area with median of 10 km2 until they departed for their autumn migration. Departure dates ranged from 21 September to 9 November. Winter TSA sizes had median of 99 km2. Adults returned to the breeding area between 12 February and 4 March. Annual breeding home ranges overlapped by approximately 84–99% indicating high site fidelity. The most utilised land cover types within winter TSAs included arable land and heterogeneous agricultural areas. Analysis of night-time roosting sites showed a substantial preference for high voltage pylons compared to trees. Our results could benefit conservation planning and species management practices, focusing on both improving the safety of anthropogenic elements and increasing habitat diversity.

A Scale Sequence Object-based Convolutional Neural Network (SS-OCNN) for crop classification from fine spatial resolution remotely sensed imagery

ABSTRACT The highly dynamic nature of agro-ecosystems in space and time usually leads to high intra-class variance and low inter-class separability in the fine spatial resolution (FSR) remotely sensed imagery. This makes traditional classifiers essentially relying on spectral information for crop mapping from FSR imagery an extremely challenging task. To mine effectively the rich spectral and spatial information in FSR imagery, this paper proposed a Scale Sequence Object-based Convolutional Neural Network (SS-OCNN) that classifies images at the object level by taking segmented objects (crop parcels) as basic units of analysis, thus, ensuring that the boundaries between crop parcels are delineated precisely. These segmented objects were subsequently classified using a CNN model integrated with an automatically generated scale sequence of input patch sizes. This scale sequence can fuse effectively the features learned at different scales by transforming progressively the information extracted at small scales to larger scales. The effectiveness of the SS-OCNN was investigated using two heterogeneous agricultural areas with FSR SAR and optical imagery, respectively. Experimental results revealed that the SS-OCNN consistently achieved the most accurate classification results. The SS-OCNN, thus, provides a new paradigm for crop classification over heterogeneous areas using FSR imagery, and has a wide application prospect.

Assessing Changes in Ecosystem Service Values over 1985–2050 in Response to Land Use and Land Cover Dynamics in Abaya-Chamo Basin, Southern Ethiopia

This study evaluated the effect of Land Use and Land Cover (LULC) dynamics on the value of ecosystem services in Abaya-Chamo basin over 1985–2050. The main objectives of the study were to estimate the value of ecosystem services of Abaya-Chamo basin using local and global ecosystem service value coefficients, assess how it changes over time, and develop tools to inform policy and public decision-making to protect lands and waters in the region. The study utilized observed (1985 and 2010) and predicted (2030 and 2050) LULC datasets and ecosystem service value coefficients obtained from publications in peer-reviewed scientific journals. The results indicated that the total ecosystem service value of Abaya-Chamo basin was 12.13 billion USD in 1985 and 12.45 billion USD in 2010. The value is predicted to increase to 12.47 billion USD by the year 2050, which is 2.84% (344.5 million USD) higher than the total value of ecosystem services of the basin in 1985. Although the total ecosystem service value of the basin showed a slight increase over the study period, it was observed that the total value of services obtained from natural ecosystems is expected to decline by 36.24% between 1985 and 2050. The losses of services obtained from natural ecosystems, such as water regulation and erosion control, are major concern as the consequence has already been reported in the basin in the form of reduced water quality and productivity of the lakes due to an increased soil erosion and sediment transport in the basin. Therefore, special attention should be given to the rehabilitation of degraded ecosystems and the protection of remaining natural vegetation and water bodies to enhance natural capital and ecosystem services in the basin. A large-scale dissemination of eco-agricultural land use practices, which provide multiple ecosystem services (such as agroforestry and heterogeneous agricultural areas) in the basin, needs to be considered in the future.

Land cover transitions and changing climate conditions in the Polish Carpathians: Assessment and management implications

AbstractWidespread, human‐induced land cover (LC) transitions in areas surrounding national parks and nature reserves, accompanied by changing climate conditions, can trigger serious consequences for these natural environments and their ecosystems. The aim of the study was to assess the direction and magnitude of transitions in LC in the Polish Carpathians since 1990 for determining the current status of land degradation neutrality and future degradation risk as well as to analyze concomitant changes in climate conditions to enable sustainable land management. The study area encompasses six national parks with the United Nations Educational, Scientific, and Cultural Organization biosphere reserves, several dozen nature reserves, and landscape parks and is a key source of drinking water in Poland. We studied detailed changes in LC (13 classes). The Wilcoxon signed rank test indicated significant increases in built‐up areas (urban fabric and industrial/transport infrastructure), waters, dense forest cover, and herbaceous vegetation but a decrease in heterogeneous agricultural areas. On the basis of two new methods, we assessed the LC transitions for 20 mountain catchments and for the entire Polish Carpathians. Although we found a slight positive transition in LC for the entire Polish Carpathians, clearly negative transitions occurred in the five analyzed catchments, including those covering two national parks. These LC transitions are accompanied by changing climate conditions with significant increases in air temperature and precipitation. The ongoing intensive urbanization in the studied mountain region, which is accompanied by significant regional warming, implies the need to apply sustainable management practices that will avoid or reduce degradation in the catchments involved.

GIS Analysis of Land-Use Change in Threatened Landscapes by Xylella fastidiosa

Land-use/land-cover analysis using Geographic Information System (GIS) application can describe and quantify the transformation of the landscape, evaluating the effectiveness of municipal planning in driving urban expansion. This approach was applied in the municipality of Spongano (Salento, South Italy) in order to evaluate the spatial heterogeneity and the transformations of the land use/land cover from 1988 to 2016. This approach was also used to examine the spread of Xylella fastidiosa, which is a plant pathogen of global importance that is reshaping the Salento landscape. The land-use maps are based on the CORINE Land Cover project classification, while the topological consistency was verified through field surveys. A change detection analysis was carried out using the land-use maps of 1988 and 2016. The most extensive land-use class is olive groves (34–36%), followed by non-irrigated arable lands and shrub and/or herbaceous vegetation associations. The main transition of land involved non-irrigated arable lands, which lost 76 ha and 23 ha to shrub and olive areas, respectively. Meanwhile, the artificial surfaces class doubled its extension, which involved mainly the transition from shrub and heterogeneous agricultural areas. However, the olive groves class is threatened by the dramatic phytosanitary condition of the area, indicating a compromised agroecosystem, which is causing a de facto transition into unproductive areas. The results highlight the inconsistency between what was planned by the urban plan in the past and how the landscape of Spongano has been changed over time. This evidence suggests that it is necessary to develop a plan based on learning by doing, in order to shape and adapt the processes of territorial transformation to the unpredictability of the ecologic, social, and economic systems, as well as ensure that these processes are always focused on environmental issues.

Continuous Daily Evapotranspiration Estimation at the Field-Scale over Heterogeneous Agricultural Areas by Fusing ASTER and MODIS Data

Continuous daily evapotranspiration (ET) monitoring at the field-scale is crucial for water resource management in irrigated agricultural areas in arid regions. Here, an integrated framework for daily ET, with the required spatiotemporal resolution, is described. Multi-scale surface energy balance algorithm evaluations and a data fusion algorithm are combined to optimally exploit the spatial and temporal characteristics of image datasets, collected by the advanced space-borne thermal emission reflectance radiometer (ASTER) and the moderate resolution imaging spectroradiometer (MODIS). Through combination with a linear unmixing-based method, the spatial and temporal adaptive reflectance fusion model (STARFM) is modified to generate high-resolution ET estimates for heterogeneous areas. The performance of this methodology was evaluated for irrigated agricultural fields in arid and semiarid areas of Northwest China. Compared with the original STARFM, a significant improvement in daily ET estimation accuracy was obtained by the modified STARFM (overall mean absolute percentage error (MAP): 12.9% vs. 17.2%; root mean square error (RMSE): 0.7 mm d−1 vs. 1.2 mm d−1). The modified STARFM additionally preserved more spatial details than the original STARFM for heterogeneous agricultural fields, and provided field-to-field variability in water use. Improvements were further evident in the continuous daily ET, where the day-to-day dynamics of ET estimates were captured. ET data fusion provides a unique means of monitoring continuous daily crop ET values at the field-scale in agricultural areas, and may have value in supporting operational water management decisions.

Optimally Heterogeneous Irrigation for Precision Agriculture Using Wireless Sensor Networks

An optimally heterogeneous irrigation (OHI) system using a wireless sensor network is developed for agricultural water irrigation, whereby a region, such as a field, is divided into a number of heterogeneous agricultural areas. An extended Kalman filter (EKF) is adopted to filter the system state including the sensed soil moisture and temperature from the associated noisy measurements. EKF is also used to predict the next system states. After that, the suboptimal irrigation water amount for each crop is proactively computed according to the crop requirements, the predicted system state and the soil conditions so that water irrigation utilization and crop yields are improved subject to the overall residual water available below a predefined level. A random bit climbing optimization method is employed to determine the suboptimal water amount for each area so that the proposed objectives are satisfied. Simulation results are compared with other traditional irrigation schemes and show that the proposed OHI approach improves water utilization, meets the heterogeneous crop requirements, copes with different soil types, prioritises crop classes and in turn enhances crop yields.

Evaluation of full-polarimetric parameters for vegetation monitoring in rabi (winter) season

Remote sensing data particularly Polarimetric Synthetic Aperture Radar (Pol SAR) data has shown promising results in crop monitoring and classification with reasonably high accuracy in tropical countries like India. Our study explores the use polarimetric SAR data for crop discrimination by evaluating different polarimetric parameters and various decomposition techniques using single date fine quad-pol C-band RADARSAT-2 dataset over heterogeneous agricultural area of Mehsana district of Gujarat state in India. Vegetation parameter, Radar Vegetation Index (RVI) and five decomposition techniques (e.g. H/A/α, Freeman-2, Freeman-3, Van Zyl-3 and Krogager) based on incoherent and coherent decompositions were selected to generate input images of classification. RVI shows good correlation with the crop stage at higher biomass with high value of RVI and with urban and water body with lower values of RVI respectively. H/A/α and its combinations i.e. (H-A) and (1-H)(1-A) show good results for discriminating land cover with different scattering mechanisms. Freeman-2, Freeman-3, Van Zyl-3 and Krogager are also evaluated for classification capability between various land covers and different crop types at different phenological stages. In 3-component decompositions, Freeman gives better results compared to other decomposition techniques for discriminating agricultural crops and natural vegetation. VanZyl decomposition overestimates surface component for agricultural crops and vegetation compared to Freeman 3-component decomposition. Krogager decomposition gives better seperability for man-made targets. The limitations of optical data for discrimination of crops based on biophysical parameters at various crop stages with similar spectral signature can be overcome by even single date full polarimetric SAR data with different decomposition techniques.