Search

This study investigates the efficacy of Synthetic Aperture Radar (SAR)-based vegetation indexes for filling gaps in the optical-driven Leaf Area Index (LAI) time series. The statistical properties of coherent (e.g., interferometric coherence) and incoherent (e.g., backscattered signal) SAR vegetation indexes are systematically studied, including their correlation with LAI measurements and significance for LAI reconstruction. First, the Multi-Output Gaussian Process (MOGP) algorithm is selected, analyzed, and subsequently improved to handle the non-Gaussian distribution of the exploited SAR indexes. Hence, a refined MOGP method incorporating a quantile-transform (QT) operation is proposed. Experiments focus on the Arborea zone in Sardinia, Italy, exploiting one year of optical and radar images from the European Copernicus Sentinel-1/2 sensors. The results prove the usefulness of the refined MOGP model in obtaining LAI time series with reduced uncertainties (R2 = 0.9/0.7 training/validation) and filling gaps in optical-based LAI observations, reconstructing feasible crop dynamic along the season. The study also provides insights into phenological state evolution and implications for future applications of the presented method.

The rice growing district in northwestern Italy, where paddies were traditionally flooded throughout spring, was interested by a general decrease of standing water presence caused by the adoption of dry seeding crop practices, with consequences for water management and for the ecology of breeding waterbirds. This communication analyses changes in flooding dynamics in the last four years, estimating them from MODIS data and comparing results with previous knowledge of the same study area. Results highlighted an intensification of the phenomenon in the north-western regions (–3.3 ± 0.6% per year in the period 2013–2021) and the almost complete loss of flooded surfaces east to the Ticino river (reaching in 2021 5% of the flooded extension estimated in 2000). Such findings highlight the importance of monitoring this phenomenon – considered by other authors as the biggest anthropogenic change in surface water of all Europe since 2000 – in near real time from remotely sensed data to monitor dynamics and support sustainable management of water usage at the district level.

How accurately do Sentinel-2 (S2) images describe vine row spatial variability? Can they produce effective management zones (MZs) for precision viticulture? S2 and UAV datasets acquired over two years for different drip-irrigated vineyards in the Colli Morenici region (northern Italy) were used to assess the actual need to use UAV-NDVI maps instead of S2 images to obtain effective MZ maps. First, the correlation between S2 and UAV-NDVI values was investigated. Secondly, contingency matrices and dichotomous tables (considering UAV-MZ maps as a reference) were developed to compare MZ maps produced using S2 and UAV imagery. Moreover, data on grape production and quality were analyzed through linear discrimination analyses (LDA) to evaluate the effectiveness of S2-MZs and UAV-MZs to explain spatial variability in yield and quality data. The outcomes highlight that S2 images can be quite good tools to manage fertilization based on the within-field vigor variability, of which they capture the main features. Nevertheless, as S2-MZs with low and high vigor were over-estimated, S2-MZ maps cannot be used for high-accuracy input management. From the LDA results, the UAV-MZs appeared slightly more performant than the S2-MZs in explaining the variability in grape quality and yield, especially in the case of low-vigor MZs.

At present, it is critical to accurately monitor wheat crops to help decision-making processes in precision agriculture. This research aims to retrieve various wheat crop traits from hyperspectral data using machine learning regression algorithms (MLRAs) and dimensionality reduction (DR) techniques. This experiment was conducted in an agricultural field in Arborea, Oristano-Sardinia, Italy, with different factors such as cultivars, N-treatments, and soil ploughing conditions. Hyperspectral data were acquired on the ground using a full-range Spectral Evolution spectrometer (350–2500 nm). Four DR techniques, including (i) variable influence on projection (VIP), (ii) principal component analysis (PCA), (iii) vegetation indices (VIs), and (iv) spectroscopic feature (SF) calculation, were undertaken to reduce the dimension of the hyperspectral data while maintaining the information content. We used five MLRA models, including (i) partial least squares regression (PLSR), (ii) random forest (RF), (iii) support vector regression (SVR), (iv) Gaussian process regression (GPR), and (v) neural network (NN), to retrieve wheat traits at either leaf and canopy levels. The studied traits were leaf area index (LAI), leaf and canopy water content (LWC and CWC), leaf and canopy chlorophyll content (LCC and CCC), and leaf and canopy nitrogen content (LNC and CNC). MLRA models were able to accurately retrieve wheat traits at the canopy level with PLSR and NN indicating the highest modelling performance. On the contrary, MLRA models indicated less accurate retrievals of the leaf-level traits. DR techniques were found to notably improve the retrieval accuracy of crop traits. Furthermore, the generated models were re-calibrated using soil spectra and then transferred to an airborne dataset collected using a CASI-SASI hyperspectral sensor, allowing the estimation of wheat traits across the entire field. The predicted crop trait maps illustrated consistent patterns while also preserving the real-field characteristics well. Lastly, a statistical paired t-test was undertaken to conduct a proof of concept of wheat phenotyping analysis considering the different agricultural variables across the study site. N-treatment caused significant differences in wheat crop traits in many instances, whereas the observed differences were less pronounced between the cultivars. No particular impact of soil ploughing conditions on wheat crop characteristics was found. Using such combinations of MLRA and DR techniques based on hyperspectral data can help to effectively monitor crop traits throughout the cropping seasons and can also be readily applied to other agricultural settings to help both precision farming applications and the implementation of high-throughput phenotyping solutions.

Earth observation techniques represent a reliable and faster alternative to in-situ measurements by providing spatio-temporal information on crop status. In this framework, a study was conducted to assess the performance of hybrid approaches, either standard (HYB) or exploiting an active learning optimisation strategy (HYB-AL), to estimate leaf area index (LAI) and canopy nitrogen content (CNC) from Sentinel–2 (S2) data, in rice crops. To achieve this, the PROSAIL-PRO Radiative Transfer Model (RTM) was tested. Results demonstrate that a wide range of rice spectra, simulated according to realistic crop parameters, are reliable when appropriate field background conditions are considered. Simulations were used to train a Gaussian Process Regression (GPR) algorithm. Both cross-validation and validation results showed that HYB-AL approach resulted the best performing retrieval schema. LAI estimation achieved good performance (R2=0.86; RMSE=0.54) and resulted very promising for model application in operational monitoring systems. CNC estimations showed moderate performance (R2=0.63; RMSE=0.89) due to a saturation behaviour limiting the retrieval accuracy for moderate/high CNC values, approximately above 4 [g m−2]. S2 maps of LAI and CNC provided spatio-temporal information in agreement with crop growth, nutritional status and agro-practices applied to the study area, resulting in an important contribution to precision farming applications.

Non-photosynthetic vegetation (NPV) plays a key role in soil conservation, which in turn is important in sustainable agriculture and carbon farming. For mapping NPV image spectroscopy proved to outperform multispectral sensors. PRISMA (PRecursore IperSpettrale della Missione Applicativa) is the forerunner of a new era of hyperspectral satellite missions, providing the proper spectral resolution for NPV mapping. This study takes advantage from both spectroscopy and machine-learning techniques. Exponential Gaussian Optimization was used for modelling known absorption bands (cellulose-lignin, pigments, water content and clays), resulting in a reduced feature space, which is split by a decision tree (DT) for mapping different field conditions (emerging, green and standing dead vegetation, crop residue and bare soil). DT training and validation exploited reference data, collected during PRISMA overpasses on a large farmland. Mapping results are accurate both at pixel and parcel level (O.A. > 90%; K > 0.9). Field status and crop rotation trajectories through time are derived by processing 12 images over 2020 and 2021. Results proved that PRISMA data are suitable for mapping field conditions at parcel scale with high confidence level. This is important in the perspective of other hyperspectral missions and is a premise toward quantitative estimates of NPV biophysical variable.

The spaceborne imaging spectroscopy mission PRecursore IperSpettrale della Missione Applicativa (PRISMA), launched on 22 March 2019 by the Italian Space Agency, opens new opportunities in many scientific domains, including precision farming and sustainable agriculture. This new Earth Observation (EO) data stream requires new-generation approaches for the estimation of important biophysical crop variables (BVs). In this framework, this study evaluated a hybrid approach, combining the radiative transfer model PROSAIL-PRO and several machine learning (ML) regression algorithms, for the retrieval of canopy chlorophyll content (CCC) and canopy nitrogen content (CNC) from synthetic PRISMA data. PRISMA-like data were simulated from two images acquired by the airborne sensor HyPlant, during a campaign performed in Grosseto (Italy) in 2018. CCC and CNC estimations, assessed from the best performing ML algorithms, were used to define two relations with plant nitrogen uptake (PNU). CNC proved to be slightly more correlated to PNU than CCC (R2 = 0.82 and R2 = 0.80, respectively). The CNC-PNU model was then applied to actual PRISMA images acquired in 2020. The results showed that the estimated PNU values are within the expected ranges, and the temporal trends are compatible with plant phenology stages.

The new generation of available (i.e., PRISMA, ENMAP, DESIS) and future (i.e., ESA-CHIME, NASA-SBG) spaceborne hyperspectral missions provide unprecedented data for environmental and agricultural monitoring, such as crop trait assessment. This paper focuses on retrieving two crop traits, specifically Chlorophyll and Nitrogen content at the canopy level (CCC and CNC), starting from hyperspectral images acquired during the CHIME-RCS project, exploiting a self-supervised learning (SSL) technique. SSL is a machine learning paradigm that leverages unlabeled data to generate valuable representations for downstream tasks, bridging the gap between unsupervised and supervised learning. The proposed method comprises pre-training and fine-tuning procedures: in the first stage, a de-noising Convolutional Autoencoder is trained using pairs of noisy and clean CHIME-like images; the pre-trained Encoder network is utilized as-is or fine-tuned in the second stage. The paper demonstrates the applicability of this technique in hybrid approach methods that combine Radiative Transfer Modelling (RTM) and Machine Learning Regression Algorithm (MLRA) to set up a retrieval schema able to estimate crop traits from new generation space-born hyperspectral data. The results showcase excellent prediction accuracy for estimating CCC (R2 = 0.8318; RMSE = 0.2490) and CNC (R2 = 0.9186; RMSE = 0.7908) for maize crops from CHIME-like images without requiring further ground data calibration.

Weeds are a crucial threat to agriculture, and in order to preserve crop productivity, spreading agrochemicals is a common practice with a potential negative impact on the environment. Methods that can support intelligent application are needed. Therefore, identification and mapping is a critical step in performing site-specific weed management. Unmanned aerial vehicle (UAV) data streams are considered the best for weed detection due to the high resolution and flexibility of data acquisition and the spatial explicit dimensions of imagery. However, with the existence of unstructured crop conditions and the high biological variation of weeds, it remains a difficult challenge to generate accurate weed recognition and detection models. Two critical barriers to tackling this challenge are related to (1) a lack of case-specific, large, and comprehensive weed UAV image datasets for the crop of interest, (2) defining the most appropriate computer vision (CV) weed detection models to assess the operationality of detection approaches in real case conditions. Deep Learning (DL) algorithms, appropriately trained to deal with the real case complexity of UAV data in agriculture, can provide valid alternative solutions with respect to standard CV approaches for an accurate weed recognition model. In this framework, this paper first introduces a new weed and crop dataset named Chicory Plant (CP) and then tests state-of-the-art DL algorithms for object detection. A total of 12,113 bounding box annotations were generated to identify weed targets (Mercurialis annua) from more than 3000 RGB images of chicory plantations, collected using a UAV system at various stages of crop and weed growth. Deep weed object detection was conducted by testing the most recent You Only Look Once version 7 (YOLOv7) on both the CP and publicly available datasets (Lincoln beet (LB)), for which a previous version of YOLO was used to map weeds and crops. The YOLOv7 results obtained for the CP dataset were encouraging, outperforming the other YOLO variants by producing value metrics of 56.6%, 62.1%, and 61.3% for the mAP@0.5 scores, recall, and precision, respectively. Furthermore, the YOLOv7 model applied to the LB dataset surpassed the existing published results by increasing the mAP@0.5 scores from 51% to 61%, 67.5% to 74.1%, and 34.6% to 48% for the total mAP, mAP for weeds, and mAP for sugar beets, respectively. This study illustrates the potential of the YOLOv7 model for weed detection but remarks on the fundamental needs of large-scale, annotated weed datasets to develop and evaluate models in real-case field circumstances.

Information on when and where rice is planted and harvested is important for crop management under a changing climate and for monitoring crop production for early warning and market information systems. The diversity of plant genetic, crop management, and environmental conditions leads to a wide variation in the number of rice crops per year and the dates of crop establishment and harvesting across Asia. Asia-wide rice crop calendars exist (e.g., RiceAtlas) but are based on heterogeneous data sources with varying levels of detail and are challenging to update. Earth observations can contribute to consistent and replicable crop calendars. Here we demonstrate and validate a method for generating a rice crop calendar across Asia. Our analysis at administrative unit-level is based on pixel-level analysis with the PhenoRice algorithm using MODIS imagery (2003–16) to estimate start of season (SoS) and end of season (EoS) dates. PhenoRice outputs were post-processed to generate representative statistics on the number of rice crop seasons per year and their SoS/EoS dates per administrative unit across Asia, called RICA (a RIce crop Calendar for Asia). RICA SoS and EoS dates across all seasons correlated strongly with RiceAtlas crop establishment and harvesting dates (R2 of 0.88 and 0.82 respectively, n = 1,186). The mean absolute errors were around 26 and 33 days for SoS and EoS, respectively. A detailed assessment in the Philippines where data in RiceAtlas are particularly accurate had even better results (R2 of 0.93 and 0.85 respectively, n = 131). Comparisons to other published rice calendars also suggested that RICA captured rice cropping season dates well. Our study results in a unique and validated method to estimate rice crop calendar information on continental scale from remote sensing data.

Rice mapping products were derived from Sentinel-1A and Landsat-8 OLI multi-temporal imagery over Northern Italy at the early stages of the 2015 growing season. A rule-based algorithm was applied to synthetic statistical metrics (TSDs-Temporal Spectra Descriptors) computed from temporal datasets of optical spectral indices and SAR backscattering coefficient. Temporal series are available up to the tillering/full canopy cover stage which is identified as the optimum timing for delivering in-season information on rice area (i.e. mid July). The approach relies on a-priori knowledge on crop dynamics to adapt time horizons for TSD computation and thresholds to local conditions. Output products consist of maps of rice cultivated areas, rice seeding techniques (dry and flooded rice) and flooding practices. Validation showed rice mapping overall accuracy to be 87.8% with commission and omission errors of 3.5% and 24.7%, respectively. Mapping of rice seeding technique showed good agreement with farmer declarations aggregated at the municipality scale (dry rice r2 = 0.71 and flooded rice r2 = 0.91). Finally, flood maps have an overall accuracy above 70%. Geo-products on rice areas and flooding occurrence are relevant information for water management at regional scale especially during summer in presence of multiple crops and water shortage.

Miscanthus holds a great potential in the frame of the bioeconomy, and yield prediction can help improve Miscanthus’ logistic supply chain. Breeding programs in several countries are attempting to produce high-yielding Miscanthus hybrids better adapted to different climates and end-uses. Multispectral images acquired from unmanned aerial vehicles (UAVs) in Italy and in the UK in 2021 and 2022 were used to investigate the feasibility of high-throughput phenotyping (HTP) of novel Miscanthus hybrids for yield prediction and crop traits estimation. An intercalibration procedure was performed using simulated data from the PROSAIL model to link vegetation indices (VIs) derived from two different multispectral sensors. The random forest algorithm estimated with good accuracy yield traits (light interception, plant height, green leaf biomass, and standing biomass) using 15 VIs time series, and predicted yield using peak descriptors derived from these VIs time series with root mean square error of 2.3 Mg DM ha−1. The study demonstrates the potential of UAVs’ multispectral images in HTP applications and in yield prediction, providing important information needed to increase sustainable biomass production.

In the next few years, the new Copernicus Hyperspectral Imaging Mission (CHIME) is foreseen to be launched by the European Space Agency (ESA). This mission will provide an unprecedented amount of hyperspectral data, enabling new research possibilities within several fields of natural resources, including the “agriculture and food security” domain. In order to efficiently exploit this upcoming hyperspectral data stream, new processing methods and techniques need to be studied and implemented. In this work, the hybrid approach (HYB) and its variant, featuring sampling dimensionality reduction through active learning heuristics (HAL), were applied to CHIME-like data to evaluate the retrieval of crop traits, such as chlorophyll and nitrogen content at both leaf (LCC and LNC) and canopy level (CCC and CNC). The results showed that HYB was able to provide reliable estimations at canopy level (R2 = 0.79, RMSE = 0.38 g m−2 for CCC and R2 = 0.84, RMSE = 1.10 g m−2 for CNC) but failed at leaf level. The HAL approach improved retrieval accuracy at canopy level (best metric: R2 = 0.88 and RMSE = 0.21 g m−2 for CCC; R2 = 0.93 and RMSE = 0.71 g m−2 for CNC), providing good results also at leaf level (best metrics: R2 = 0.72 and RMSE = 3.31 μg cm−2 for LCC; R2 = 0.56 and RMSE = 0.02 mg cm−2 for LNC). The promising results obtained through the hybrid approach support the feasibility of an operational retrieval of chlorophyll and nitrogen content, e.g., in the framework of the future CHIME mission. However, further efforts are required to investigate the approach across different years, sites and crop types in order to improve its transferability to other contexts.

In this work we propose an approach for mapping flooded areas from Sentinel-2 MSI (Multispectral Instrument) data based on soft fuzzy integration of evidence scores derived from both band combinations (i.e. Spectral Indices - SIs) and components of the Hue, Saturation and Value (HSV) colour transformation. Evidence scores are integrated with Ordered Weighted Averaging (OWA) operators, which model user’s decision attitude varying smoothly between optimistic and pessimistic approach. Output is a map of global evidence degree showing the plausibility of being flooded for each pixel of the input Sentinel-2 (S2) image. Algorithm set up and validation were carried out with data over three sites in Italy where water surfaces are extracted from stable water bodies (lakes and rivers), natural hazard flooding, and irrigated paddy rice fields. Validation showed more than satisfactory accuracy for the OR-like OWA operators (F-score > 0.90) with performance slightly decreased (F-score

The paper proposes a fully automatic algorithm approach to map burned areas from remote sensing characterized by human interpretable mapping criteria and explainable results. This approach is partially knowledge-driven and partially data-driven. It exploits active fire points to train the fusion function of factors deemed influential in determining the evidence of burned conditions from reflectance values of multispectral Sentinel-2 (S2) data. The fusion function is used to compute a map of seeds (burned pixels) that are adaptively expanded by applying a Region Growing (RG) algorithm to generate the final burned area map. The fusion function is an Ordered Weighted Averaging (OWA) operator, learnt through the application of a machine learning (ML) algorithm from a set of highly reliable fire points. Its semantics are characterized by two measures, the degrees of pessimism/optimism and democracy/monarchy. The former allows the prediction of the results of the fusion as affected by more false positives (commission errors) than false negatives (omission errors) in the case of pessimism, or vice versa; the latter foresees if there are only a few highly influential factors or many low influential ones that determine the result. The prediction on the degree of pessimism/optimism allows the expansion of the seeds to be appropriately tuned by selecting the most suited growing layer for the RG algorithm thus adapting the algorithm to the context. The paper illustrates the application of the automatic method in four study areas in southern Europe to map burned areas for the 2017 fire season. Thematic accuracy at each site was assessed by comparison to reference perimeters to prove the adaptability of the approach to the context; estimated average accuracy metrics are omission error = 0.057, commission error = 0.068, Dice coefficient = 0.94 and relative bias = 0.0046.

In this paper, we provide an innovative contribution in the research domain dedicated to crop mapping by exploiting the of Sentinel-2 satellite images time series, with the specific aim to extract information on “where and when” crops are grown. The final goal is to set up a workflow able to reliably identify (classify) the different crops that are grown in a given area by exploiting an end-to-end (3+2)D convolutional neural network (CNN) for semantic segmentation. The method also has the ambition to provide information, at pixel level, regarding the period in which a given crop is cultivated during the season. To this end, we propose a solution called Class Activation Interval (CAI) which allows us to interpret, for each pixel, the reasoning made by CNN in the classification determining in which time interval, of the input time series, the class is likely to be present or not. Our experiments, using a public domain dataset, show that the approach is able to accurately detect crop classes with an overall accuracy of about 93% and that the network can detect discriminatory time intervals in which crop is cultivated. These results have twofold importance: (i) demonstrate the ability of the network to correctly interpret the investigated physical process (i.e., bare soil condition, plant growth, senescence and harvesting according to specific cultivated variety) and (ii) provide further information to the end-user (e.g., the presence of crops and its temporal dynamics).

The leaf area index (LAI) is a key biophysical variable for agroecosystem monitoring, as well as a relevant state variable in crop modelling. For this reason, temporal and spatial determination of LAI are required to improve the understanding of several land surface processes related to vegetation dynamics and crop growth. Despite the large number of retrieved LAI products and the efforts to develop new and updated algorithms for LAI estimation, the available products are not yet capable of capturing site-specific variability, as requested in many agricultural applications. The objective of this study was to evaluate the potential of non-parametric approaches for multi-temporal LAI retrieval by Sentinel-2 multispectral data, in comparison with a VI-based parametric approach. For this purpose, we built a large database combining a multispectral satellite data set and ground LAI measurements collected over two growing seasons (2018 and 2019), including three crops (i.e., winter wheat, maize, and alfalfa) characterized by different growing cycles and canopy structures, and considering different agronomic conditions (i.e., at three farms in three different sites). The accuracy of parametric and non-parametric methods for LAI estimation was assessed by cross-validation (CV) at both the pixel and field levels over mixed-crop (MC) and crop-specific (CS) data sets. Overall, the non-parametric approach showed a higher accuracy of prediction at pixel level than parametric methods, and it was also observed that Gaussian Process Regression (GPR) did not provide any significant difference (p-value > 0.05) between the predicted values of LAI in the MC and CS data sets, regardless of the crop. Indeed, GPR at the field level showed a cross-validated coefficient of determination (R2CV) higher than 0.80 for all three crops.

Sentinel-2 (S2) multi-spectral instrument (MSI) images are used in an automated approach built on fuzzy set theory and a region growing (RG) algorithm to identify areas affected by fires in Mediterranean regions. S2 spectral bands and their post- and pre-fire date (Δpost-pre) difference are interpreted as evidence of burn through soft constraints of membership functions defined from statistics of burned/unburned training regions; evidence of burn brought by the S2 spectral bands (partial evidence) is integrated using ordered weighted averaging (OWA) operators that provide synthetic score layers of likelihood of burn (global evidence of burn) that are combined in an RG algorithm. The algorithm is defined over a training site located in Italy, Vesuvius National Park, where membership functions are defined and OWA and RG algorithms are first tested. Over this site, validation is carried out by comparison with reference fire perimeters derived from supervised classification of very high-resolution (VHR) PlanetScope images leading to more than satisfactory results with Dice coefficient > 0.84, commission error < 0.22 and omission error < 0.15. The algorithm is tested for exportability over five sites in Portugal (1), Spain (2) and Greece (2) to evaluate the performance by comparison with fire reference perimeters derived from the Copernicus Emergency Management Service (EMS) database. In these sites, we estimate commission error < 0.15, omission error < 0.1 and Dice coefficient > 0.9 with accuracy in some cases greater than values obtained in the training site. Regression analysis confirmed the satisfactory accuracy levels achieved over all sites. The algorithm proposed offers the advantages of being least dependent on a priori/supervised selection for input bands (by building on the integration of redundant partial burn evidence) and for criteria/threshold to obtain segmentation into burned/unburned areas.

This study introduces a first assessment of the capabilities of PRISMA (PRecursore IperSpettrale della Missione Applicativa)—the new hyperspectral satellite sensor of the Italian Space Agency (ASI)—for Non-Photosynthetic Vegetation (NPV) monitoring, a topic which is becoming very relevant in the field of sustainable agriculture, being an indicator of crop residue (CR) presence in the field. Data-sets collected during the mission validation phase in croplands are used for mapping the NPV presence and for modelling the diagnostic absorption band of cellulose around 2.1 μm with an Exponential Gaussian Optimization approach, in the perspective of the prediction of the abundance of crop residues. Results proved that PRISMA data are suitable for these tasks, and call for further investigation to achieve quantitative estimates of specific biophysical variables, also in the framework of other hyperspectral missions.

Soil properties variability is a factor that greatly influences cereals crops production and interacts with a proper assessment of crop nutritional status, which is fundamental to support site-specific management able to guarantee a sustainable crop production. Several management strategies of precision agriculture are now available to adjust the nitrogen (N) input to the actual crop needs. Many of the methods have been developed for proximal sensors, but increasing attention is being given to satellite-based N management systems, many of which rely on the assessment of the N status of crops. In this study, the reliability of the crop nutritional status assessment through the estimation of the nitrogen nutrition index (NNI) from Sentinel-2 (S2) satellite images was examined, focusing of the impact of soil properties variability for crop nitrogen deficiency monitoring. Vegetation indices (VIs) and biophysical variables (BVs), such as the green area index (GAI_S2), leaf chlorophyll content (Cab_S2), and canopy chlorophyll content (CCC_S2), derived from S2 imagery, were used to investigate plant N status and NNI retrieval, in the perspective of its use for guiding site-specific N fertilization. Field experiments were conducted on maize and on durum wheat, manipulating 4 groups of plots, according to soil characteristics identified by a soil map and quantified by soil samples analysis, with different N treatments. Field data collection highlighted different responses of the crops to N rate and soil type in terms of NNI, biomass (W), and nitrogen concentration (Na%). For both crops, plots in one soil class (FOR1) evidenced considerably lower values of BVs and stress conditions with respect to others soil classes even for high N rates. Soil samples analyses showed for FOR1 soil class statistically significant differences for pH, compared to the other soil classes, indicating that this property could be a limiting factor for nutrient absorption, hence crop growth, regardless of the amount of N distributed to the crop. The correlation analysis between measured crop related BVs and satellite-based products (VIs and S2_BVs) shows that it is possible to: (i) directly derive NNI from CCC_S2 (R2 = 0.76) and either normalized difference red edge index (NDRE) for maize (R2 = 0.79) or transformed chlorophyll absorption ratio index (TCARI) for durum wheat (R2 = 0.61); (ii) indirectly estimate NNI as the ratio of plant nitrogen uptake (PNUa) and critical plant nitrogen uptake (PNUc) derived using CCC_S2 (R2 = 0.77) and GAI_S2 (R2 = 0.68), respectively. Results of this study confirm that NNI is a good indicator to monitor plants N status, but also highlights the importance of linking this information to soil properties to support N site-specific fertilization in the precision agriculture framework. These findings contribute to rational agro-practices devoted to avoid N fertilization excesses and consequent environmental losses, bringing out the real limiting factors for optimal crop growth.

Compact multi-spectral sensors that can be mounted on lightweight drones are now widely available and applied within the geo- and environmental sciences. However; the spatial consistency and radiometric quality of data from such sensors is relatively poorly explored beyond the lab; in operational settings and against other sensors. This study explores the extent to which accurate hemispherical-conical reflectance factors (HCRF) and vegetation indices (specifically: normalised difference vegetation index (NDVI) and chlorophyll red-edge index (CHL)) can be derived from a low-cost multispectral drone-mounted sensor (Parrot Sequoia). The drone datasets were assessed using reference panels and a high quality 1 m resolution reference dataset collected near-simultaneously by an airborne imaging spectrometer (HyPlant). Relative errors relating to the radiometric calibration to HCRF values were in the 4 to 15% range whereas deviations assessed for a maize field case study were larger (5 to 28%). Drone-derived vegetation indices showed relatively good agreement for NDVI with both HyPlant and Sentinel 2 products (R2 = 0.91). The HCRF; NDVI and CHL products from the Sequoia showed bias for high and low reflective surfaces. The spatial consistency of the products was high with minimal view angle effects in visible bands. In summary; compact multi-spectral sensors such as the Parrot Sequoia show good potential for use in index-based vegetation monitoring studies across scales but care must be taken when assuming derived HCRF to represent the true optical properties of the imaged surface.

The paper proposes a transparent approach for mapping the status of environmental phenomena from multisource information based on both soft computing and machine learning. It is transparent, intended as human understandable as far as the employed criteria, and both knowledge and data-driven. It exploits remote sensing experts’ interpretations to define the contributing factors from which partial evidence of the environmental status are computed by processing multispectral images. Furthermore, it computes an environmental status indicator (ESI) map by aggregating the partial evidence degrees through a learning mechanism, exploiting volunteered geographic information (VGI). The approach is capable of capturing the specificities of local context, as well as to cope with the subjectivity of experts’ interpretations. The proposal is applied to map the status of standing water areas (i.e., water bodies and rivers and human-driven or natural hazard flooding) using multispectral optical images by ESA Sentinel-2 sources. VGI comprises georeferenced observations created both in situ by agronomists using a mobile application and by photointerpreters interacting with a geographic information system (GIS) using several information layers. Results of the validation experiments were performed in three areas of Northern Italy characterized by distinct ecosystems. The proposal showed better performances than traditional methods based on single spectral indexes.

Asian countries strongly depend on rice production for food security. The major rice-growing season (June to October) is highly exposed to the risk of tropical storm related damage. Unbiased and transparent approaches to assess the risk of rice crop damage are essential to support mitigation and disaster response strategies in the region. This study describes and demonstrates a method for rapid, pre-event crop status assessment. The ex-post test case is Typhoon Haiyan and its impact on the rice crop in Leyte Province in the Philippines. A synthetic aperture radar (SAR) derived rice area map was used to delineate the area at risk while crop status at the moment of typhoon landfall was estimated from specific time series analysis of Moderate Resolution Imaging Spectroradiometer (MODIS) data. A spatially explicit indicator of risk of standing crop loss was calculated as the time between estimated heading date and typhoon occurrence. Results of the analysis of pre- and post-event SAR images showed that 6500 ha were flooded in northeastern Leyte. This area was also the region most at risk to storm related crop damage due to late establishment of rice. Estimates highlight that about 700 ha of rice (71% of which was in northeastern Leyte) had not reached maturity at the time of the typhoon event and a further 8400 ha (84% of which was in northeastern Leyte) were likely to be not yet harvested. We demonstrated that the proposed approach can provide pre-event, in-season information on the status of rice and other field crops and the risk of damage posed by tropical storms.

The aim of this paper is to investigate how optical and Synthetic Aperture Radar (SAR) data can be combined in an integrated multi-source framework to identify burned areas at the regional scale. The proposed approach is based on the use of fuzzy sets theory and a region-growing algorithm. Landsat TM and (C-band) ENVISAT Advanced Synthetic Aperture Radar (ASAR) images acquired for the year 2003 have been processed to extract burned area maps over Portugal. Pre-post fire SAR backscatter temporal difference has been integrated with optical spectral indices to the aim of reducing confusion between burned areas and low-albedo surfaces. The output fuzzy score maps have been compared with reference fire perimeters provided by the Fire Atlas of Portugal. Results show that commission and omission errors in the output burned area maps are a function of the threshold applied to the fuzzy score maps; between the two extremes of the greatest producer’s accuracy (omission error < 10%) and user’s accuracy (commission error < 5%), an intermediate threshold value provides errors of about 20% over the study area. The integration of SAR backscatter allowed reducing local commission errors from 65.4% (using optical data, only) to 11.4%, showing to significantly mitigate local errors due to the presence of cloud shadows and wetland areas. Overall, the proposed method is flexible and open to further developments; also in the perspective of the European Space Agency (ESA) Sentinel missions operationally providing SAR and optical datasets.

This paper presents a method for mapping the nitrogen (N) status in a maize field using hyperspectral remote sensing imagery. An airborne survey was conducted with an AISA Eagle hyperspectral sensor over an experimental farm where maize (Zea mays L.) was grown with two N fertilization levels (0 and 100 kg N ha−1) in four replicates. Leaf and canopy field data were collected during the flight. The nitrogen (N) status has been estimated in this work based on the Nitrogen Nutrition Index (NNI), defined as the ratio between the leaf actual N concentration (%Na) of the crop and the minimum N content required for the maximum biomass production (critical N concentration (%Nc)) calculated through the dry mass at the time of the flight (Wflight). The inputs required to calculate the NNI (i.e., %Na and Wflight) have been estimated through regression analyses between field data and remotely sensed vegetation indices. MCARI/MTVI2 (Modified Chlorophyll Absorption Ratio Index/Modified Triangular Vegetation Index 2) showed the best performances in estimating the %Na (R2 = 0.59) and MTVI2 in estimating the Wflight (R2 = 0.80). The %Na and the Wflight were then mapped and used to compute the NNI map over the entire field. The NNI map agreed with the NNI estimated using field data through traditional destructive measurements (R2 = 0.70) confirming the potential of using remotely sensed indices to assess the crop N condition. Finally, a method to derive a pixel based variable rate N fertilization map was proposed as the difference between the actual N content and the optimal N content. We think that the proposed operational methodology is promising for precision farming since it represents an innovative attempt to derive a variable rate N fertilization map based on the actual crop N status from an aerial hyperspectral image.

Rangeland monitoring services require the capability to investigate vegetation condition and to assess biomass production, especially in areas where local livelihood depends on rangeland status. Remote sensing solutions are strongly recommended, where the systematic acquisition of field data is not feasible and does not guarantee properly describing the spatio-temporal dynamics of wide areas. Recent research on semi-arid rangelands has focused its attention on the evaporative fraction (EF), a key factor to estimate evapotranspiration (ET) in the energy balance (EB) algorithm. EF is strongly linked to the vegetation water status, and works conducted on eddy covariance towers used this parameter to increase the performances of satellite-based biomass estimation. In this work, a method to estimate EF from MODIS products, originally developed for evapotranspiration estimation, is tested and evaluated. Results show that the EF estimation from low spatial resolution over wide semi-arid area is feasible. Estimated EF resulted in being well correlated to field ET measurements, and the spatial patterns of EF maps are in agreement with the well-known climatic and landscape Sahelian features. The preliminary test on rangeland biomass production shows that satellite-retrieved EF as a water availability factor significantly increased the capacity of a remote sensing operational product to detect the variability of the field biomass measurements.

Accurate nitrogen (N) management is crucial for the economic and environmental sustainability of cropping systems. Different methods have been developed to increase the efficiency of N fertilizations. However, their costs and/or low usability have often prevented their adoption in operational contexts. We developed a diagnostic system to support topdressing N fertilization based on the use of smart apps to derive a N nutritional index (NNI; actual/critical plant N content). The system was tested on paddy rice via dedicated field experiments, where the smart apps PocketLAI and PocketN were used to estimate, respectively, critical (from leaf area index) and actual plant N content. Results highlighted the system’s capability to correctly detect the conditions of N stress (NNI < 1) and N surplus (NNI > 1), thereby effectively supporting topdressing fertilizations. A resource-efficient methodology to derive PocketN calibration curves for different varieties—needed to extend the system to new contexts—was also developed and successfully evaluated on 43 widely grown European varieties. The widespread availability of smartphones and the possibility to integrate NNI and remote sensing technologies to derive variable rate fertilization maps generate new opportunities for supporting N management under real farming conditions.

The intensive rice cultivation area in northwestern Italy hosts the largest surface of rice paddies in Europe, and it is valued as a substantial habitat for aquatic biodiversity, with the paddies acting as a surrogate for the lost natural wetlands. The extent of submerged paddies strictly depends on crop management practices: in this framework, the recent diffusion of rice seeding in dry conditions has led to a reduction of flooded surfaces during spring and could have contributed to the observed decline of the populations of some waterbird species that exploit rice fields as foraging habitat. In order to test the existence and magnitude of a decreasing trend in the extent of submerged rice paddies during the rice-sowing period, MODIS remotely-sensed data were used to estimate the extent of the average flooded surface and the proportion of flooded rice fields in the years 2000–2016 during the nesting period of waterbirds. A general reduction of flooded rice fields during the rice-sowing season was observed, averaging − 0.86 ± 0.20 % per year (p-value < 0.01). Overall, the loss in submerged surface area during the sowing season reached 44 % of the original extent in 2016, with a peak of 78 % in the sub-districts to the east of the Ticino River. Results highlight the usefulness of remote sensing data and techniques to map and monitor water dynamics within rice cropping systems. These techniques could be of key importance to analyze the effects at the regional scale of the recent increase of dry-seeded rice cultivations on watershed recharge and water runoff and to interpret the decline of breeding waterbirds via a loss of foraging habitat.

Leaf area index (LAI) is a crucial variable in the modelling of many hydrological processes. Destructive sampling of LAI is extremely time-consuming, thus not suitable for monitoring temporal/spatial variations of the variable. In the last fifty years optical instruments retrieving LAI from more easily measurable variables (i.e. transmitted radiation through canopies) have been developed. Several instruments are available on the market, but very few are the studies comparing LAI estimates in agricultural crops. In this paper three optical instruments are compared with destructive sampling for a maize crop located in Northern Italy. Determinations were carried out on three plots (replicates) before and after successive thinning of plant populations. Destructively sampled LAI ranged from 4.9 m2m-2 (no thinning) to 1.2 m2m- 2 (maximum thinning). Correlation analysis showed that estimates by the AccuPAR-80, the hemispherical camera (“effective” and “true” LAI) and the LAI- 2000 (in the standard configuration, i.e. five zenithal rings, and excluding the fifth ring) were well correlated with destructive measurements (R2≥0.95). Anyway, if for the AccuPAR-80 the regression line was close to the 1:1 line, the “true LAI” by hemispherical photography tended to overestimate destructively sampled LAI for low values while the “effective LAI” and the LAI-2000 to underestimate it for high values (in a minor way for the LAI-2000 when the fifth ring was removed). Results from the ANOVA and the Tukey T test for two-factor experiments with replicates showed that only the “effective LAI” retrieved by hemispherical photographs and the estimates provided by the LAI-2000 in the standard configuration (five rings) were statistically different from destructive measurements.

Crop insurance is a viable solution to reduce the vulnerability of smallholder farmers to risks from pest and disease outbreaks, extreme weather events, and market shocks that threaten their household food and income security. In developing and emerging countries, the implementation of area yield-based insurance, the form of crop insurance preferred by clients and industry, is constrained by the limited availability of detailed historical yield records. Remote-sensing technology can help to fill this gap by providing an unbiased and replicable source of the needed data. This study is dedicated to demonstrating and validating the methodology of remote sensing and crop growth model-based rice yield estimation with the intention of historical yield data generation for application in crop insurance. The developed system combines MODIS and SAR-based remote-sensing data to generate spatially explicit inputs for rice using a crop growth model. MODIS reflectance data were used to generate multitemporal LAI maps using the inverted Radiative Transfer Model (RTM). SAR data were used to generate rice area maps using MAPScape-RICE to mask LAI map products for further processing, including smoothing with logistic function and running yield simulation using the ORYZA crop growth model facilitated by the Rice Yield Estimation System (Rice-YES). Results from this study indicate that the approach of assimilating MODIS and SAR data into a crop growth model can generate well-adjusted yield estimates that adequately describe spatial yield distribution in the study area while reliably replicating official yield data with root mean square error, RMSE, of 0.30 and 0.46 t ha−1 (normalized root mean square error, NRMSE of 5% and 8%) for the 2016 spring and summer seasons, respectively, in the Red River Delta of Vietnam, as evaluated at district level aggregation. The information from remote-sensing technology was also useful for identifying geographic locations with peculiarity in the timing of rice establishment, leaf growth, and yield level, and thus contributing to the spatial targeting of further investigation and interventions needed to reduce yield gaps.

Agricultural monitoring has greatly benefited from the increased availability of a wide variety of remote-sensed satellite imagery, ground-sensed data (e.g., weather station networks) and crop models, delivering a wealth of actionable information to stakeholders to better streamline and improve agricultural practices. Nevertheless, as the degree of sophistication of agriculture monitoring systems increases, significant challenges arise due to the handling and integration of multi-scale data sources to present information to decision-makers in a way which is useful, understandable and user friendly. To address these issues, in this article we present the conceptual architecture and service-oriented implementation of a regional geoportal, specifically focused on rice crop monitoring in order to perform unified monitoring with a supporting system at regional scale. It is capable of storing, processing, managing, serving and visualizing monitoring and generated data products with different granularity and originating from different data sources. Specifically, we focus on data sources and data flow, and their importance for and in relation to different stakeholders. In the context of an EU-funded research project, we present an implementation of the regional geoportal for rice monitoring, which is currently in use in Europe’s three largest rice-producing countries, Italy, Greece and Spain.

The triangle method has been applied to derive a weekly indicator of evaporative fraction on vegetated areas in a temperate region in Northern Italy. Daily MODIS Aqua Land Surface Temperature (MYD11A1) data has been combined with air temperature maps and 8-day composite MODIS NDVI (MOD13Q1/MYD13Q1) data to estimate the Evaporative Fraction (EF) at 1 km resolution, on a daily basis. Measurements at two eddy covariance towers located within the study area have been exploited to assess the reliability of satellite based EF estimations as well as the robustness of input data. Weekly syntheses of the daily EF indicator (EFw) were then derived at regional scale for the years 2010, 2011 and 2012 as a proxy of overall surface moisture condition. EFw showed a temporal behavior consistent with growing cycles and agro-practices of the main crops cultivated in the study area (rice, forages and corn). Comparison with official regional corn yield data showed that variations in EFw cumulated over summer are related with crop production shortages induced by water scarcity. These results suggest that weekly-averaged EF estimated from MODIS data is sensible to water stress conditions and can be used as an indicator of crops’ moisture conditions at agronomical district level. Advantages and disadvantages of the proposed approach to provide information useful to issue operational near real time bulletins on crop conditions at regional scale are discussed.

This paper presents and evaluates multitemporal LAI estimates derived from Sentinel-2A data on rice cultivated area identified using time series of Sentinel-1A images over the main European rice districts for the 2016 crop season [...]

Identifying managed flooding in paddy fields is commonly used in remote sensing to detect rice. Such flooding, followed by rapid vegetation growth, is a reliable indicator to discriminate rice. Spectral indices (SIs) are often used to perform this task. However, little work has been done on determining which spectral combination in the form of Normalised Difference Spectral Indices (NDSIs) is most appropriate for surface water detection or which thresholds are most robust to separate water from other surfaces in operational contexts. To address this, we conducted analyses on satellite and field spectral data from an agronomic experiment as well as on real farming situations with different soil and plant conditions. Firstly, we review and select NDSIs proposed in the literature, including a new combination of visible and shortwave infrared bands. Secondly, we analyse spectroradiometric field data and satellite data to evaluate mixed pixel effects. Thirdly, we analyse MODIS data and Landsat data at four sites in Europe and Asia to assess NDSI performance in real-world conditions. Finally, we test the performance of the NDSIs on MODIS temporal profiles in the four sites. We also compared the NDSIs against a combined index previously used for agronomic flood detection. Analyses suggest that NDSIs using MODIS bands 4 and 7, 1 and 7, 4 and 6 or 1 and 6 perform best. A common threshold for each NDSI across all sites was more appropriate than locally adaptive thresholds. In general, NDSIs that use band 7 have a negligible increase in Commission Error over those that use band 6 but are more sensitive to water presence in mixed land cover conditions typical of moderate spatial resolution analyses. The best performing NDSI is comparable to the combined index but with less variability in performance across sites, suggesting a more succinct and robust flood detection method.

Currently, the best practice to support land planning calls for the development of Spatial Data Infrastructures (SDI) capable of integrating both geospatial datasets and time series information from multiple sources, e.g., multitemporal satellite data and Volunteered Geographic Information (VGI). This paper describes an original OGC standard interoperable SDI architecture and a geospatial data and metadata workflow for creating and managing multisource heterogeneous geospatial datasets and time series, and discusses it in the framework of the Space4Agri project study case developed to support the agricultural sector in Lombardy region, Northern Italy. The main novel contributions go beyond the application domain for which the SDI has been developed and are the following: the ingestion within an a-centric SDI, potentially distributed in several nodes on the Internet to support scalability, of products derived by processing remote sensing images, authoritative data, georeferenced in-situ measurements and voluntary information (VGI) created by farmers and agronomists using an original Smart App; the workflow automation for publishing sets and time series of heterogeneous multisource geospatial data and relative web services; and, finally, the project geoportal, that can ease the analysis of the geospatial datasets and time series by providing complex intelligent spatio-temporal query and answering facilities.

Leaf area index (LAI) is a key biophysical parameter used to determine foliage cover and crop growth in environmental studies in order to assess crop yield. Frequently, plant canopy analyzers (LAI-2000) and digital cameras for hemispherical photography (DHP) are used for indirect effective plant area index (PAIeff) estimates. Nevertheless, these instruments are expensive and have the disadvantages of low portability and maintenance. Recently, a smartphone app called PocketLAI was presented and tested for acquiring PAIeff measurements. It was used during an entire rice season for indirect PAIeff estimations and for deriving reference high-resolution PAIeff maps. Ground PAIeff values acquired with PocketLAI, LAI-2000, and DHP were well correlated (R2 = 0.95, RMSE = 0.21 m2/m2 for Licor-2000, and R2 = 0.94, RMSE = 0.6 m2/m2 for DHP). Complementary data such as phenology and leaf chlorophyll content were acquired to complement seasonal rice plant information provided by PAIeff. High-resolution PAIeff maps, which can be used for the validation of remote sensing products, have been derived using a global transfer function (TF) made of several measuring dates and their associated satellite radiances.