In - season progressive crop type mapping in war affected Ukraine

Crop type identification and mapping have been a classic issue essential for agriculture characterisation and food security as well as crop health monitoring. Remote sensing was proven to be an efficient tool to define and study agriculture. The complementarity between optical and radar data can hugely improve crop type identification and mapping. This document presents an overview of more than 40 recent works between 2013 and 2019, related to crop type mapping using satellite imagery, and points the general techniques used. Different classification algorithms was studied and compared, as well as the comparison of the inputs, optimal bands and polarization for radar data, and process giving the best results. It is often concluded that fusion improves results when compared with single data using. Nevertheless, it had been challenging to combine datasets from sensors that had different physical concepts, and progress in this domain require the development of systematic procedures.

LiDAR data are becoming increasingly available, which has opened up many new applications. One such application is crop type mapping. Accurate crop type maps are critical for monitoring water use, estimating harvests and in precision agriculture. The traditional approach to obtaining maps of cultivated fields is by manually digitizing the fields from satellite or aerial imagery and then assigning crop type labels to each field – often informed by data collected during ground and aerial surveys. However, manual digitizing and labeling is time-consuming, expensive and subject to human error. Automated remote sensing methods is a cost-effective alternative, with machine learning gaining popularity for classifying crop types. This study evaluated the use of LiDAR data, Sentinel-2 imagery, aerial imagery and machine learning for differentiating five crop types in an intensively cultivated area. Different combinations of the three datasets were evaluated along with ten machine learning. The classification results were interpreted by comparing overall accuracies, kappa, standard deviation and f-score. It was found that LiDAR data successfully differentiated between different crop types, with XGBoost providing the highest overall accuracy of 87.8%. Furthermore, the crop type maps produced using the LiDAR data were in general agreement with those obtained by using Sentinel-2 data, with LiDAR obtaining a mean overall accuracy of 84.3% and Sentinel-2 a mean overall accuracy of 83.6%. However, the combination of all three datasets proved to be the most effective at differentiating between the crop types, with RF providing the highest overall accuracy of 94.4%. These findings provide a foundation for selecting the appropriate combination of remotely sensed data sources and machine learning algorithms for operational crop type mapping.

Crop type information is essential for many practical applications, yet its mapping is often constrained by inherent characteristics of most farming areas, such as fragmentation and small farm plots, changes in crop morphology across the season, and cloud cover. This study investigated whether these limitations could be overcome by using time-series of Synthetic Aperture Radar (SAR) and crop phenological information combined with different Dynamic Time Warping implementation strategies. Focusing on a fragmented landscape with small farm plots in the Netherlands, we used Sentinel-1 dual polarimetry (VV + VH) and TerraSAR-X single polarimetry (HH) images and the Dutch Basic Registration of Crop Plots (BRP) dataset for training and validation. Image pre-processing was followed by the generation of radar vegetation indices and polarimetric decomposition. Crop-specific responses to incident radar signal were analyzed, as well as the accuracy of the crop classification by Time-Weighted Dynamic Time Warping (twDTW) using either backscatter bands only or backscatter bands in combination with derived indices and polarimetric decomposition features. In addition, two further modified Dynamic Time Warping strategies, namely Variable Time Weight Dynamic Time Warping (vtwDTW) and Angular Metric for Shape Similarity (AMSS), were tested for their performance. Furthermore, we investigated the accuracy performance of a decision level fusion of TerraSAR-X and Sentinel-1 classification outputs. Results show that even in a fragmented landscape with relatively small plots (around 0.08 ha), crop types can be successfully mapped by using decision level fusion of the twDTW results of both sensors, reaching an accuracy of 77.1%. When using twDTW on Sentinel-1 (VV + VH) only, including Ratio, MRVI, and DPSVI indices, overall accuracy reached 69.5%; without those indices, accuracy was slightly lower (67.5%). Merging six different grain crops with similar leaf geometry into winter grains and summer grains improved classification accuracy to 80.6%. Our findings demonstrate that twDTW on SAR imagery allows to map crop types in fragmented landscapes with relatively small farm plots, offering potential for crop type mapping in areas with smallholder farming.

MODIS phenology-derived, multi-year distribution of conterminous U.S. crop types

A survey of Ardeid nesting colonies in central Guizhou, southwestern China in May 2006, which covered about one-third of the area of this province, recorded a total of 1587 nests of five species, i.e., Little Egret (<i>Egretta garzetta</i>), Cattle Egret (<i>Bubulcus ibis</i>), Chinese Pond Heron (<i>Ardeola bacchus</i>), Black-crowned Night Heron (<i>Nycticorax nycticorax</i>) and Grey Heron (<i>Ardea cinerea</i>) at 11 nesting colonies. The largest colonies were recorded at Fengyunyan and Yanfu resorts, the smallest one at Luobolin. The Little Egret was the dominant nesting species (49.7% of the total number of nests) and the Grey Heron was the least abundant (0.1%). All nesting colonies were located in the northern and central parts of Guizhou; no colonies were found in the Leigongshan area, the southern part of this province. The distribution of nesting colonies in central Guizhou appears to be affected by the relative composition of winter (wheat and vegetable) and summer (rice) crops during the breeding season (between late March and June). No colonies were found around farmlands with winter crops and most colonies were situated around rice paddies. The farmland use pattern is affected by rainfall. The summer crop is delayed if the rainy season starts late and the rainfall is light. Priority for conservation of the Ardeids in central Guizhou should be given to the larger colonies i.e., Yanfu and Fengyunyan resorts.

Effect of tillage and crop type on soil respiration in a long-term field experiment on chernozem soil under temperate climate

Implementing appropriate operating rule curves for water resources systems and hydroclimatic conditions significantly reduce damages floods and droughts damages in the downstream area. This paper uses simulation-optimization approach to establish a multi-purpose reservoir's rule curve. The hedging method is utilized for drought, and the multi-stage flood routing method is used for floods. The melody search algorithm is employed as the optimization algorithm. The Karkhe Reservoir is a case study, facing irregular water distribution and hydrological challenges from extensive domestic and agricultural water usage, varying cultivation patterns, and flood susceptibility. The region grows two types of crops - autumn and summer crops. Autumn cultivation is fundamental and strategic, but water use for summer or water-based crops reduces water resources for it. Meeting water demands from September to November is another challenge due to the overlapping water needs of summer and autumn crops. Significant changes in the upstream and downstream areas, including alterations in the shape and water resource utilization of the catchment area, as well as changes in the rivers' morphological condition and water carrying capacity, make it a constant challenge to determine the optimal water level for the reservoir. The results demonstrate the satisfactory performance of the optimized rule curve.

Productivity and profitability of modern irrigation methods through the application of on-farm drip irrigation on some crops in the Northern Nile Delta of Egypt

Crop type mapping by using transfer learning

In the Yaqui Valley, northwest Mexico, the crop sequence that is becoming more common consists of planting wheat (Triticum aestivum L.) as a winter crop on a raised bed followed by maize (Zea mays L.) as a summer crop. In this area, straw of both winter and summer crops is commonly burned. The consequences of burning crop residues on crop yields in the Yaqui Valley have not previously been documented, and alternative practices have not been proposed. A 5‐yr study was conducted at the CIANO (Centro de Investigaciones Agrı́colas del Noroeste) experiment station in Sonora, Mexico, to compare the effects of burning with other straw management strategies on wheat and maize yields. We tested two tillage systems (conventional‐tilled bed, CTB, and permanent bed, PB), five straw management treatments (incorporated with CTB and straw as stubble, partly removed, removed, or burned with PB), and seven N treatments, five applied preplant (0, 75, 150, 225, and 300 kg N ha−1) and two at the 1st node stage (150 and 300 kg N ha−1) of wheat. Maize following wheat received a uniform application of 150 kg N ha−1. The combination of PB and straw as stubble produced superior maize and wheat grain yields in high‐yielding environments; in low‐yielding environments, PB–straw burned produced greater wheat grain yields. Nitrogen fertilizer application of 150 and 300 kg N ha−1 at the 1st node stage of wheat increased grain yields compared with preplant N fertilizer applications. Permanent beds combined with retaining all crop residues in the soil as stubble have the potential to increase both wheat and maize yields in the Yaqui Valley.

A branch canal was selected in El Sefsaf canal command area which located in Sidi Salem district in Kafr El sheikh Governorate ( North Delta ) for using geography information system (GIS) for mapping cropping pattern and water requirements for winter and summer crops before irrigation improvement and after improving. El Sefsaf canal is an earth branch canal located at km 51.800 on the left side of Meet Yazied main canal ; a carrier canal located on the left side of Bahr Shebeen canal at Km 96.500, the 63.00 Km long canal feeds an area of about 210,000Fed.Distributed through 19 branch canals The length of EL-Sefsaf canal that is about 3.400Km which served a command area of about 700 Fed . design of bed width vary between 2.5 m and 1.5 m , while the design maximum water level vary between 2.80 m and 2.50 m, while the actual maximum water level vary between 1.50 m and 1.60 m. The study was carried out during four seasons started from Nov. 2003 and finished in the end of summer season 2008. This period covered two summer seasons ( summer 2004 and summer 2008 ) and two winter seasons ( winter 2003/2004 and winter 2007/2008 ) Total crop water requirements in EL Sefsaf canal command area could be summarized as follows: Summer crops : The total water requirements of Rice were 1753213.59 and 1537013.18 m3 in 2004 and 2008 seasons respectively. While it were 1200734.54 and 549805.78 m3 in 2004 and 2008 respectively for cotton crop. Also the total water requirements of Maize crop were 111488.49 and 19168.44 m3 for the above mentioned seasons respectively. The highest water requirements as recorded with Rice crop. The peak demand were in July and August. Winter crops : The total water requirements of Barseem were 982490.09 and 516100.68 m3 in 2003/2004 and 2007/2008 seasons respectively. On the other hand the total water requirements of Wheat crop were 1056627.12 and 667397.01 m3 for the stated seasons respectively. Finally the total water requirements of Sugarbeet crop were 554260.24 m3 in 2003/2004 season , and 68416.21 m3 in 2007/2008 season. The peak demand were in Marsh and April.

Cross model validation for a diversified cropping system

ContextBiodiversity in agroecosystems has experienced significant declines in species richness due to intensive agricultural practices. Historically, diverse agricultural landscapes have been replaced by nutrient-rich monocultures. To improve the situation, it is important to find out what are the attributes of these landscapes that support the highest species richness.ObjectivesThis study investigates the relationships of farmland bird species richness to field size, diversity of crop types and landscape elements (expressing different kinds of habitat heterogeneity), areas of winter and spring crops (i.e., crops sown in the autumn and in the spring, respectively), and invertebrate food availability. The research objective is to find out which of these factors are linked to the highest richness.MethodsBird species were surveyed using point counts during the breeding season at 52 sites of varying field sizes, landscape element composition, and crop types in open agricultural landscapes in northwestern Hungary, Europe. Food availability was expressed as invertebrate abundance, diversity, and biomass, respectively.ResultsBird species richness increased with landscape element diversity and invertebrate abundance, while the field size showed opposing effects depending on crop type. Smaller field sizes were more beneficial in the case of winter crops, but larger fields supported more farmland bird species in the case of spring crops. The abundance of invertebrates was particularly high in alfalfa and fallow fields.ConclusionsThe value of open farmland for farmland bird species richness can be improved by enhancing diversity of landscape elements (e.g. by adding small water bodies to landscape mosaic), increasing invertebrate abundance (e.g. by reducing pesticide use), reducing the size of fields covered by winter crops and supporting the spring crops.

The creation of crop type maps from satellite data has proven challenging and is often impeded by a lack of accurate in situ data. Street-level imagery represents a new potential source of in situ data that may aid crop type mapping, but it requires automated algorithms to recognize the features of interest. This paper aims to demonstrate a method for crop type (i.e., maize, wheat and others) recognition from street-level imagery based on a convolutional neural network using a bottom-up approach. We trained the model with a highly accurate dataset of crowdsourced labelled street-level imagery using the Picture Pile application. The classification results achieved an AUC of 0.87 for wheat, 0.85 for maize and 0.73 for others. Given that wheat and maize are two of the most common food crops grown globally, combined with an ever-increasing amount of available street-level imagery, this approach could help address the need for improved global crop type monitoring. Challenges remain in addressing the noise aspect of street-level imagery (i.e., buildings, hedgerows, automobiles, etc.) and uncertainties due to differences in the time of day and location. Such an approach could also be applied to developing other in situ data sets from street-level imagery, e.g., for land use mapping or socioeconomic indicators.

With the latest development and increasing availability of high spatial resolution sensors, earth observation technology offers a viable solution for crop identification and management. There is a strong need to produce accurate, reliable and up to date crop type maps for sustainable agriculture monitoring and management. In this study, RapidEye, the first high-resolution multi-spectral satellite system that operationally provides a Red-edge channel, was used to test the potential of the data for crop type mapping. This study was investigated at a selected region mostly covered with agricultural fields locates in the low lands of Menemen (İzmir) Plain, TURKEY. The potential of the three classification algorithms such as Maximum Likelihood Classification, Support Vector Machine and Object Based Image Analysis is tested. Accuracy assessment of land cover maps has been performed through error matrix and kappa indexes. The results highlighted that all selected classifiers as highly useful (over 90%) in mapping of crop types in the study region however the object-based approach slightly outperforming the Support Vector Machine classification by both overall accuracy and Kappa statistics. The success of selected methods also underlines the potential of RapidEye data for mapping crop types in Aegean region.