Monitoring agricultural crops is necessary for decision-making in the field. However, it is known that in some regions and periods, cloud cover makes this activity difficult to carry out in a systematic way throughout the phenological cycle of crops. This circumstance opens up opportunities for techniques involving radar sensors, resulting in images that are free of cloud effects. In this context, the objective of this work was to obtain a normalized different vegetation index (NDVI) cloudless product (NDVI_nc) by modeling Sentinel 2 NDVI using different regression techniques and the Sentinel 1 radar backscatter as input. To do this, we used four pairs of Sentinel 2 and Sentinel 1 images on coincident days, aiming to achieve the greatest range of NDVI values for agricultural crops (soybean and maize). These coincident pairs were the only ones in which the percentage of clouds was not equal to 100% for 33 central pivot areas in western Bahia, Brazil. The dataset used for NDVI_nc modeling was divided into two subsets: training and validation. The training and validation datasets were from the period from 24 June 2017 to 19 July 2018 (four pairs of images). The best performing model was used in a temporal analysis from 02 October 2017 to 08 August 2018, totaling 55 Sentinel 2 images and 25 Sentinel 1 images. The selection of the best regression algorithm was based on two validation methodologies: K-fold cross-validation (k = 10) and holdout. We tested four modeling approaches with eight regression algorithms. The random forest was the algorithm that presented the best statistical metrics, regardless of the validation methodology and the approach used. Therefore, this model was applied to a time series of Sentinel 1 images in order to demonstrate the robustness and applicability of the model created. We observed that the data derived from Sentinel 1 allowed us to model, with great reliability, the NDVI of agricultural crops throughout the phenological cycle, making the methodology developed in this work a relevant solution for the monitoring of various regions, regardless of cloud cover.

Droughts are major natural disasters that affect many parts of the world all years and recently affected one of the major conilon coffee-producing regions of the world in state of Espírito Santo, which caused a huge crisis in the sector. Therefore, the objective of this study was to conduct an analysis with technical-scientific basis of the real impact of drought associated with high temperatures and irradiances on the conilon coffee (Coffea canephora Pierre ex Froehner) plantations located in the north, northwest, and northeast regions of the state of Espírito Santo, Brazil. Data from 2010 to 2016 of rainfall, air temperature, production, yield, planted area and surface remote sensing were obtained from different sources, statistically analyzed, and correlated. The 2015/2016 season was the most affected by the drought and high temperatures (mean annual above 26 °C) because, in addition to the adverse weather conditions, coffee plants were already damaged by the climatic conditions of the previous season. The increase in air temperature has higher impact (negative) on production than the decrease in annual precipitation. The average annual air temperatures in the two harvest seasons that stood out for the lowest yields (i.e. 2012/2013 and 2015/2016) were approximately 1 °C higher than in the previous seasons. In addition, in the 2015/2016 season, the average annual air temperature was the highest in the entire series. The spatial and temporal distribution of Enhanced Vegetation Index values enabled the detection and perception of droughts in the conilon coffee-producing regions of Espírito Santo. The rainfall volume accumulated in the periods from September to December and from April to August are the ones that most affect coffee yield. The conilon coffee plantations in these regions are susceptible to new climate extremes, as they continue to be managed under irrigation and full sun. The adoption of agroforestry systems and construction of small reservoirs can be useful to alleviate these climate effects, reducing the risk of coffee production losses and contributing to the sustainability of crops in Espírito Santo.

Hydrological models are valuable tools for developing streamflow predictions in unmonitored catchments to increase our understanding of hydrological processes. A recent effort has been made in the development of hybrid (conceptual/machine learning) models that can preserve some of the hydrological processes represented by conceptual models and can improve streamflow predictions. However, these studies have not explored how the data-driven component of hybrid models resolved runoff routing. In this study, explainable artificial intelligence (XAI) techniques are used to turn a ‘black-box’ model into a ‘glass box’ model. The hybrid models reduced the root-mean-square error of the simulated streamflow values by approximately 27, 50, and 24% for stations 17120000, 27380000, and 33680000, respectively, relative to the traditional method. XAI techniques helped unveil the importance of accounting for soil moisture in hydrological models. Differing from purely data-driven hydrological models, the inclusion of the production storage in the proposed hybrid model, which is responsible for estimating the water balance, reduced the short- and long-term dependencies of input variables for streamflow prediction. In addition, soil moisture controlled water percolation, which was the main predictor of streamflow. This finding is because soil moisture controls the underlying mechanisms of groundwater flow into river streams.

Small reservoirs play a key role in the Brazilian savannah (Cerrado), making irrigation feasible and contributing to the economic development and social well-being of the population. A lack of information on factors, such as evaporative water loss, has an impact on the design and management of these reservoirs, as well as on regional water safety. Acquiring this information is crucial for hydrologists to develop more effective water resource management strategies and policies. This study assesses the performance of a diverse number of methods that are used to estimate evaporation and provides evaporation probability curves on a fortnightly period for small reservoirs in the Brazilian savannah region. Evaporation data were collected for a small water reservoir located in the Buriti Vermelho watershed, a typical dam of the Brazilian savannah region. Among the assessed methods, those of Kohler et al. (1955) and Linacre (1993) presented the best performances on both the daily and monthly scales for evaporation estimates. By simulating the evaporation rates for a timeseries, an increasing trend in evaporation was observed for the transition between the dry and wet seasons, jeopardizing double cropping in the region. The developed probability curves are an important tool for improving water resource planning and increasing the local water availability.