Abstract
Mechanisation is a key input in modern agriculture, while it accounts for a large part of crop production costs, it can bring considerable farm benefits if well managed. Models for simulated machinery costs, may not replace actual cost measurements but the information obtained through them can replace a farm's existing records, becoming more valuable to decision makers. MACHoice, a decision support system (DSS) presented in this paper, is a farm machinery cost estimator and break-even analyzer of alternatives for agricultural operations, developed using user-driven expectations and in close collaboration with agronomists and computer engineers. It integrates an innovative algorithm developed for projections of machinery costs under different rates of annual machine use and work capacity processing, which is crucial to decisions on break-even machinery alternatives. A case study based on the comparison of multiple alternatives for grape harvesting operations is presented to demonstrate the typical results that can be expected from MACHoice, and to identify its capabilities and limitations. This DSS offers an integrated and flexible analysis environment with a user-friendly graphical interface as well as a high level of automation of processing chains. The DSS-output consists of charts and tables, evidencing the differences related to costs and carbon emissions between the options inserted by the user for the different intensity of yearly work proceeded. MACHoice is an interactive web-based tool that can be accessed freely for non-commercial use by every known browser.

Abstract
This study aimed to estimate the daily crop evapotranspiration (ETc) of soilless cut 'Red Naomi' roses, cultivated in a commercial glass greenhouse, using climatic and crop predictors. A multiple stepwise regression technique was applied for estimating ETc using the daily relative humidity, stem leaf area and number of leaves of the bended stems. The model explained 90% of the daily ETc variability (R-2 = 0.90, n = 33, P < 0.0001) measured by weighing lysimeters. The mean relative difference between the observed and the estimated daily ETc was 9.1%. The methodology revealed a high accuracy and precision in the estimation of daily ETc.

Abstract
Soil erosion constitute a major threat to human lives and assets worldwide, as well as a major environmental disturbance. The Revised Universal Soil Loss Equation (RUSLE) integrated with Geographical Information System (GIS) has been the most widely used model in predicting and mapping soil erosion loss. Remote sensing has particular utility for soil loss model applications, providing observations on several key aspects of Land use and Land cover (LULC) linked to the cover-management factor C of the RUSLE, over wide areas and in consistent and repeatable measurements. A free and open source GIS application coupled with remote sensing data was developed under QGIS software allowing to improve the C factor functionality: (i) automatically download satellite images; (ii) clip with the study case and; (ii) perform a supervised or unsupervised classification, in order to obtain the land cover classification and produce the final C map. One of the most efficient supervised classification algorithms is the Support Vector Machine (SVM). Random Forest (RF) is also an easy-to-use machine learning algorithm for supervised classification. The automation of this functionality was based in the R and SAGA software, both integrated in QGIS. To perform the supervised classification, SVM and RF methods were incorporated. The overall accuracy and Kappa values are also automatically obtained by the R script and GRASS algorithms, which allows to evaluate the result obtained. To perform the unsupervised classification K-means algorithm from SAGA was used. This updating in RUSLE application improve the results obtained for C factor and help us to obtain a most accurate estimation of RUSLE erosion risk map. The application was tested using Sentinel 2A images in two different periods, after and before the forest fire event in Coimbra region, Portugal. In the end, the three resulted maps from SVM, RF and K-means classification were compared.

Abstract
Wildfires constitute an important threat to human lives and livelihoods worldwide, as well as a major ecological disturbance. However, available wildfire databases often provide incomplete or inaccurate information, namely regarding the timing and extension of fire events. In this study, we described a generic framework to compare, rank and combine multiple remotely-sensed indicators of wildfire disturbances, in order to not only select the best indicators for each specific case, as well as to provide multi-indicator consensus approaches that can be used to detect wildfire disturbances in space and time. For this end, we compared the performance of different remotely-sensed variables to discriminate burned areas, by applying a simple change-point analysis procedure on time-series of MODIS imagery for the northern half of Portugal, without external information (e.g. active fire maps). Overall, our results highlight the importance of adopting a multi-indicator consensus approach for mapping and detecting wildfire disturbances at a regional scale, that allows to profit from spectral indices capturing different aspects of the Earth's surface, and derived from distinct regions of the electromagnetic spectrum. Finally, we argue that the framework here described can be used: (i) in a wide variety of geographical and environmental contexts; (ii) to support the identification of the best possible remotely-sensed functional indicators of wildfire disturbance; and (iii) for improving and complementing incomplete wildfire databases.

Abstract
Grapevine yield prediction during phenostage and particularly, before harvest is highly significant as advanced forecasting could be a great value for superior grapevine management. The main contribution of the current study is to develop predictive model for each phenology that predicts yield during growing stages of grapevine and to identify highly relevant predictive variables. Current study uses climatic conditions, grapevine yield, phenological dates, fertilizer information, soil analysis and maturation index data to construct the relational dataset. After words, we use several approaches to pre-process the data to put it into tabular format. For instance, generalization of climatic variables using phenological dates. Random Forest, LASSO and Elasticnet in generalized linear models, and Spikeslab are feature selection embedded methods which are used to overcome dataset dimensionality issue. We used 10-fold cross validation to evaluate predictive model by partitioning the dataset into training set to train the model and test set to evaluate it by calculating Root Mean Squared Error (RMSE) and Relative Root Mean Squared Error (RRMSE). Results of the study show that rf_PF, rf_PC and rf_MH are optimal models for flowering (PF), colouring (PC) and harvest (MH) phenology respectively which estimate 1484.5, 1504.2 and 1459.4 (Kg/ha) low RMSE and 24.6%, 24.9% and 24.2% RRMSE, respectively as compared to other models. These models also identify some derived climatic variables as major variables for grapevine yield prediction. The reliability and early-indication ability of these forecast models justify their use by institutions and economists in decision making, adoption of technical improvements, and fraud detection. © 2019 Asian Agricultural and Biological Engineering Association

Abstract
Autonomous Unmanned Aerial Vehicles (UAVs) become an important field of research in which multiple applications can be designed, such as surveillance, deliveries, and others. Thus, studies aiming to improve the performance of these vehicles are being proposed: from new sensing solutions to more robust control techniques. Additionally, the autonomous UAV has challenges in flight stages as the landing. This procedure needs to be performed safely with a reduced error margin in static and dynamic targets. To solve this imperative issue, many applications with computer vision and control theory have been developed. Therefore, this paper presents an alternative method to train a multilayer perceptron neural network based on fuzzy Mamdani logic to control the landing of a UAV on an artificial marker. The advantage of this method is the reduction in computational complexity while maintaining the characteristics and intelligence of the fuzzy logic controller. Results are presented with simulation and real tests for static and dynamic landing spots. For the real experiments, a quadcopter with an onboard computer and ROS is used.