Search

Accurately estimating latent heat flux (LE) is crucial for achieving efficiency in irrigation. It is a fundamental component in determining the actual evapotranspiration (ETa), which in turn, quantifies the amount of water lost that needs to be adequately compensated through irrigation. Empirical and physics-based models have extensive input data and site-specific limitations when estimating the LE. In contrast, the emergence of data-driven techniques combined with remote sensing has shown promising results for LE estimation with minimal and easy-to-obtain input data. This paper evaluates two machine learning-based approaches for estimating the LE. The first uses climate data, the Normalized Difference Vegetation Index (NDVI), and Land Surface Temperature (LST), while the second uses climate data combined with raw satellite bands. In-situ data were sourced from a flux station installed in our study area. The data include air temperatures (Ta), global solar radiation (Rg), and measured LE for the period 2015-2018. The study uses Landsat 8 as a remote sensing data source. At first, 12 raw available bands were downloaded. The LST is then derived from thermal bands using the Split Window algorithm (SW) and the NDVI from optical bands. During machine learning modeling, the CatBoost model is fed, trained, and evaluated using the two data combination approaches. Cross-validation of 3-folds gave an average RMSE of 27.54 W.nr2 using the first approach and 27.05 W.nr2 using the second approach. Results raise the question: Do we need additional computational layers when working with remote sensing products combined with machine learning? Future work is to generalize the approach and test it for other applications such as soil moisture retrieval, and yield prediction.

In several areas, many social, economic, and physical subsystems interact around water resources. Integrated water management is applied to maximize economic and social welfare in an equitable manner without compromising the sustainability of vital ecosystems, mainly in hydrologic-stressed areas. The Souss-Massa basin, with its semi-arid climate, has a significant demand for agricultural, industrial, tourism, and domestic water. It constitutes a complex system where the lack of knowledge of all the interacting subsystems has led to a shortage of water in quantity and quality. The objective of this study is to investigate the interactions between supply and demand at different stages using a System Dynamics (SD) approach. The model developed promotes a holistic understanding of the interactions between the different problem indicators that operate in water resources management in order to support decision-making action and successfully manage water resources at the Souss-Massa basin scale. The chosen performance indicator is based on the achievement of a baseline sustainability index (SI) defined as the ratio of available water to supply water that should be higher than 20% to avoid a water stress situation. The multisource data were gathered from different government agencies for the period spanning between 2007 and 2020. The results showed that the current policies do not lead to sustainable water management. Groundwater withdrawals have increased considerably, from 747 Mm3 in 2007 to 4884 Mm3 in 2020. The balance between water supply and demand is only reached for three years, 2010, 2015, and 2018, without ever reaching an SI of 20%. The sensitivity analysis showed that the sustainability of water resources in the Souss-Massa basin is mainly impacted by the availability of surface water, irrigated areas, and irrigation efficiency. This study will be of great interest to policymakers to provide optimal and sustainable water management strategies based on improved water use efficiency, and to contribute to the sustainable development agenda in arid and semi-arid regions. [ABSTRACT FROM AUTHOR]

Smart management of weather data is an essential step toward implementing sustainability and precision in agriculture. It represents an important input for numerous tasks, such as crop growth, development, yield, and irrigation scheduling, to name a few. Advances in technology allow collecting this weather data from heterogeneous sources with high temporal resolution and at low cost. Generating and using these data in their raw form makes no sense, and therefore implementing adequate infrastructure and tools is necessary. For that purpose, this paper presents a smart weather data management system evaluated using data from a meteorological station installed in our study area covering the period from 2013 to 2020 at a half-hourly scale. The proposed system makes use of state-of-the-art statistical methods, machine learning, and deep learning models to derive actionable insights from these raw data. The general architecture is made up of four layers: data acquisition, data storage, data processing, and application layers. The data sources include real-time sensors, IoT devices, reanalysis data, and raw files. The data are then checked for errors and missing values using a proposed method based on ERA5-Land reanalysis data and deep learning. The resulting coefficient of determination (R2) and Root Mean Squared Error (RMSE) for this method were 0.96 and 0.04, respectively, for the scaled air temperature estimate. The MongoDB NoSQL database is used for storage thanks to its ability to deal with real-world big data. The system offers various services such as (i) weather time series forecasts, (ii) visualization and analysis of meteorological data, and (iii) the use of machine learning to estimate the reference evapotranspiration (ET0) needed for efficient irrigation. To this, the platform uses the XGBoost model to achieve the precision of the Penman–Monteith method while using a limited number of meteorological variables (air temperature and global solar radiation). Results for this approach give R2 = 0.97 and RMSE = 0.07. This system represents the first incremental step toward implementing smart and sustainable agriculture in Morocco. [ABSTRACT FROM AUTHOR]

Environmental flows are unanimously considered to be one of the most comprehensive indicators of the rivers health and their capacities to provide ecosystem goods and services. In this study, the objective was to predict the response of environmental flow components in a typical North African rivers network to future climate change. The study watershed is Bouregreg watershed (BW) in Morocco. To achieve this objective, a hybrid approach was build based on the semi-distributed model Soil and Water Assessment Tool (SWAT) and the Indicators of Hydrologic Alteration program (IHA). Data of two emissions scenarios (RCP4.5 and RCP8.5) from a downscaled Global Circulation Model were used to force the hybrid SWAT-IHA to calculate modifications of BW's environmental flow components in 2085-2100 period. Results showed that BW will experience climatic changes under both scenarios. Most of the environmental flow attributes will be modified within the study period: loss of natural flow variability due to shift in exceedance probability of low flows (up to 40%), decrease of monthly low flows, forward shift in high flow timing (up to 50%), and alteration of both the duration and the rise rates of floods. BW's streams responded unequally to the simulated changes in terms of the altered attributes as well as the degree of the alteration. This study confirmed the ability of the developed modeling approach to monitor environmental flow parameters for the first time in Morocco, and contributed in highlighting the necessity of proactive long term strategies to protect riverine ecosystems in North Africa watersheds. [ABSTRACT FROM AUTHOR]

This research is focused on developing an AI model that utilizes multispectral camera data from the Souss-Massa region. The model aims to estimate the yield and identify a range of diseases in Argan trees through meticulous on-field investigations. Initially, the work is focused on understanding the resistance of Argan plants against different diseases, based on non-irrigated and irrigated Argan trees as well as planted ones. The results show that disease resistance is high in the case of non-irrigated Argan trees and low in the case of irrigated trees. In addition, we conducted a detailed study of the Argan trees to provide a comprehensive view of the plant’s health. Utilizing machine-learning techniques, the yield estimation model suggests that it is possible to achieve up to 97% accuracy in yield estimation, processing data at an impressive rate of 33 images per second. After careful consideration and analysis, we have concluded that machine counting is the most suitable technique for Argan plants. Machine counting and disease detection offer high precision, fast and efficient data processing and cost-effectiveness. Additionally, it is less labour-intensive and can be easily integrated into the existing production process. [ABSTRACT FROM AUTHOR]

Abstract: Efficient water resources management is an issue of major importance in the field of sustainable development, especially in the agricultural sector which represents the main consumer through irrigations. Therefore irrigation management is an important and innovating area which was the subject of several research and studies. Modeling, and more particularly, the Agent-Based Modeling (ABM), allows better representing the multiplicity of these actors, the diversity of their roles and their interactions. The main reason why we chose the agent technology in the field of gravity irrigation systems, is the complexity to manage in real-time the water distribution operations those arrive asynchronously and dynamically and to be reactive and adaptive to the dynamic and unpredictable events that characterizes the field (mainly rainy advents). Our objectives are mainly located on two levels. The first one, concerns the gravity irrigation modeling by a multi-agent technology and the agent modeling through AML language. The second one focuses on the irrigations scheduling optimization using an evolutionary algorithm. Comparisons between schedules before and after optimization are made and the results shows that our approach can be considered as an efficient tool for planning irrigation schedules by considering crops water needs. [Copyright &y& Elsevier]

This study aims to investigate the effects of an optimized sowing calendar for wheat over a surface irrigation scheme in the semi-arid region of Haouz (Morocco) on irrigation water requirements, crop growth and development and on yield. For that, a scenario-based simulation approach based on the covariance matrix adaptation–evolution strategy (CMA-ES) was proposed to optimize both the spatiotemporal distribution of sowing dates and the irrigation schedules, and then evaluate wheat crop using the 2011–2012 growing season dataset. Six sowing scenarios were simulated and compared to identify the most optimal spatiotemporal sowing calendar. The obtained results showed that with reference to the existing sowing patterns, early sowing of wheat leads to higher yields compared to late sowing (from 7.40 to 5.32 t/ha). Compared with actual conditions in the study area, the spatial heterogeneity is highly reduced, which increased equity between farmers. The results also showed that the proportion of plots irrigated in time can be increased (from 40% to 82%) compared to both the actual irrigation schedules and to previous results of irrigation optimization, which did not take into consideration sowing dates optimization. Furthermore, considerable reduction of more than 40% of applied irrigation water can be achieved by optimizing sowing dates. Thus, the proposed approach in this study is relevant for irrigation managers and farmers since it provides an insight on the consequences of their agricultural practices regarding the wheat sowing calendar and irrigation scheduling and can be implemented to recommend the best practices to adopt. [ABSTRACT FROM AUTHOR]