The drought in Serbia in the summer of 2017 heavily affected agricultural production, decreasing yields of maize, sunflower, soybean, and sugar beet. Monitoring moisture levels in crops can provide timely information about potential risk within a growing season, thus helping to create an early warning system for various stakeholders. The purpose of this study was to quantify the level of moisture stress in crops during summer and the consequences that it can have on yields. For that, maize and sunflower yield data provided by an agricultural company were used at specific parcels in the Backa region of Vojvodina province (Serbia) for 2017, 2018, 2019, and 2020. The crop moisture level was estimated at each parcel by calculating the normalized difference moisture index (NDMI) from Sentinel-2 data during the summer months (June–July–August). Based on the average NDMI value in July, the new crop moisture stress (CMS) index was introduced. The results showed that the CMS values at a specific parcel could be used for within-season estimation of maize and sunflower yield and the assessment of drought effects. The CMS index was tested for the current growing season of 2022 as an early warning system for yield reduction, demonstrating the potential to be included in a platform for digital agriculture, such as AgroSens, which is operational in Serbia.

Information on the harvest date of crops can help with logistics management in the agricultural industry, planning machinery operations and also with yield prediction modelling. In this study, the determination and prediction of harvest dates for different crops were performed by applying machine learning techniques on C-band synthetic aperture radar (SAR) data. Ground truth data were provided for the Vojvodina region (Serbia), an area with intensive agricultural production, considering winter wheat, maize and soybean fields with exact harvest dates, for the period 2017–2020, including 592 samples in total. Data from the Sentinel-1 satellite were used in the study. Time series of backscattering coefficients for vertical–horizontal (VH) and vertical–vertical (VV) polarisations, both from ascending and descending orbits, were collected from Google Earth Engine. Clustering of harvested and unharvested fields was performed with Principal Component Analysis, multidimensional scaling and t-distributed Stochastic Neighbour Embedding, for initial cluster visualization. It is shown that the separability of unharvested and harvested data in two-dimensional space does not depend on the selected method but more on the crop itself. Support Vector Machine and Multi-layer Perceptron were used as classification algorithms for harvest detection, with the former achieving higher accuracies of 79.65% for wheat, 83.41% for maize and 95.97% for soybean. Finally, regression models were developed for the prediction of the harvest date using Random Forest and the long short-term memory network, with the latter achieving better results: an R2 score of 0.72, mean absolute error of 6.80 days and root mean squared error of 9.25 days, for all crops considered together.

The drought in south-eastern Europe in the summer of 2017 heavily affected agricultural production, subsequently decreasing yields of maize. The European Drought Observatory provides Combined Drought Indicator for a 10-day period with coarse spatial resolution of 5 km, which is not localized on field level. It is derived from the combination of Standardized Precipitation Index (SPI), the Soil Moisture Index Anomaly (SMA), and the anomaly of the fraction of absorbed photosynthetically active radiation (FAPAR). Monitoring moisture levels in crops can provide timely information about the presence of abiotic stress in plants and improper development within a growing season. Heat stress and low levels of moisture in maize during summer can thereafter have detrimental consequences on yield. For that reason, in this study, the crop moisture level was estimated at specific parcels by calculating the normalized difference moisture index (NDMI) from Sentinel-2 multispectral imagery during summer months (June–July–August) and the time-series of NDMI were analyzed. Based on the average NDMI value in July, the crop moisture stress (CMS) index was calculated and divided into six classes. Maize yield data on parcel level were provided by an agricultural company for the period 2017 – 2021 in the Backa region of Vojvodina province, Serbia. Yield data for the period 2017-2020 were used to calculate average yield for each class of CMS, whereas yield data from 2021 were used for validation. Mean absolute error (MAE) and root-mean-square error (RMSE) were calculated and were around 1 t/ha. The results showed that the CMS values at a specific parcel could be used for within-season estimation of maize yield and the assessment of drought effects. Also, the CMS index was tested for the 2022 growing season which had drought hazard conditions in south-eastern Europe according to the European Drought Observatory. Expected maize yield reduction estimated for specific scouted fields showed substantial and below average yield values.

Increasing agricultural production is inevitable in the future since population growth and climate change have led to significant pressure on global food security. One of the ways is to intensify the existing cropland by multi-cropping practice, allowing multiple uses of a single field during one year.  This research aims to identify and map double-cropping land using multi-temporal Sentinel 2 imagery from 2021 and advanced machine learning models. The case study focus is on Bačka and Srem, regions located in the Autonomous Province of Vojvodina, Republic of Serbia. These regions are characterized by fertile land and widespread agriculture production. However, there is a low presence of double-cropping practice due to usually dry summers, but with a tendency to change as the number of irrigation systems increase.Considering the small amount of double-cropping fields, there is a need for direct ground truth data collection. For that reason, the first step was to reduce the area of interest to get insight into the locations of potential double-cropping land. This result was obtained by using the threshold method based on the phenology of crops during the year. The NDVI (Normalized Difference Vegetation Index) time series was utilized to define appropriate thresholds for feature two peak values to discriminate double-cropping within each pixel. The identification of the results was used on-site for collecting ground truth data. Based on the collected data and the analyzed NDVI time series, besides double-crop, three more classes of arable land were distincted and included in the classification: single winter crops, single summer crops and clover. The collected data contained 46 parcels of double crops, 43 single winter crops, 55 single summer crops and 27 parcels of clover. We used time-series images to create a dataset for training the pixel-based Random Forest classification. The results showed a very high overall accuracy of 99% and an  F-score higher than 0.9 for each of the classes.This methodology is a suitable approach for detecting double-cropping systems, with further potential to identify exact crop types and the main practice of combining crops. The findings of this study showed that only about 2% of the study area was under this production. Except for positive economic outcomes, utilizing these systems brings significant environmental benefits and rational use of the soil without expanding physical cropland but with the same advantages. Therefore, the resulting geospatial datasets of double cropping croplands could help solve important questions relevant to food security, irrigation and climate change.

Extreme compound events defined as the simultaneous occurrence of multiple natural hazards such as floods, droughts, and heatwaves, have become increasingly frequent in South East Europe in recent years. These events can have significant impacts on the region's social, economic, and environmental systems and can lead to significant human losses. Because South East is identified as a climate hot spot for future climate change and occurrence of extreme compound events, it is very important to identify and study these hot spots. This information could be useful for decision-makers and practitioners in the water management and agriculture sector, especially in the Balkan region. Here we present the first results of the study of the compound warm and dry over the Western Balkan area since compound events have not been studied over the territory of Eastern Europe since 1950 until today. Using daily data on maximum temperature and precipitation, we calculated the frequency and trends of the warm/dry (WD) indices. Trends were calculated using the Mann-Kendall trend test in R and the resolution that was used is ERA5 1950-now. Presented results are annual and also seasonal variations. The index that we used shows cold and dry events per year or season, the results indicate the rising trend over the whole territory of South East Europe, where trends were statistically significant by over 95 percent. We investigated years with recorded heat waves and the most severe droughts in the observed region in the years: 2007, 2012, 2015, and 2017. In 2007 there were more than 140 warm and dry events in the Western Balkans area, in 2012 there were between 160 and 200 warm and dry events, in 2015 more than 140 and in 2017 around 140 warm and dry events. Studying extreme compound events is very important because it helps us to better understand the underlying causes of extreme weather and other natural disasters, especially in this area of high agricultural potential. This knowledge can help farmers to make informed decisions about how to identify potential risks and develop strategies to mitigate them to maximize their yields and minimize losses.Our results highlight the need for targeted and effective risk management strategies to reduce the negative impacts of extreme compound events in South East Europe. KEY WORDSCompound events, temperature, precipitation, Eastern Europe, trends Funding: This research was supported by the EXtremeClimTwin project, which has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No952384.