Welcome to MELSpace
DSpace is a digital service that collects, preserves, and distributes digital material. Repositories are important tools for preserving an organization's legacy; they facilitate digital preservation and scholarly communication.
Recent Submissions
Developing automated machine learning approach for fast and robust crop yield prediction using a fusion of remote sensing, soil, and weather dataset
Author(s): Kheir, Ahmed M.S.; Govind, Ajit; Nangia, Vinay; Devkota Wasti, Mina; Elnashar, Abdelrazek; Omar, Mohie; Feike, Til (IOP Publishing, 2024-04-25)
Date: 2024-04-25
Type: Journal Article
Status: Open access
Estimating smallholder crop yields robustly and timely is crucial for improving agronomic practices,
determining yield gaps, guiding investment, and policymaking to ensure food security. However,
there is poor estimation of yield for most smallholders due to lack of technology, and field scale data,
particularly in Egypt. Automated machine learning (AutoML) can be used to automate the machine
learning workflow, including automatic training and optimization of multiple models within a userspecified
time frame, but it has less attention so far. Here, we combined extensive field survey yield
across wheat cultivated area in Egypt with diverse dataset of remote sensing, soil, and weather to
predict field-level wheat yield using 22 Ml models in AutoML. The models showed robust accuracies
for yield predictions, recording Willmott degree of agreement, (d>0.80) with higher accuracy when
super learner (stacked ensemble) was used (R2=0.51, d=0.82). The trained AutoML was deployed to
predict yield using remote sensing (RS) vegetative indices (VIs), demonstrating a good correlation
with actual yield (R2=0.7). This is very important since it is considered a low-cost tool and could be
used to explore early yield predictions. Since climate change has negative impacts on agricultural
production and food security with some uncertainties, AutoML was deployed to predict wheat yield
under recent climate scenarios from the Coupled Model Intercomparison Project Phase 6 (CMIP6).
These scenarios included single downscaled General Circulation Model (GCM) as CanESM5 and two
shared socioeconomic pathways (SSPs) as SSP2-4.5and SSP5-8.5during the mid-term period (2050).
The stacked ensemble model displayed declines in yield of 21% and5%under SSP5-8.5 and SSP2-4.5
respectively during mid-century, with higher uncertainty under the highest emission scenario (SSP5-
8.5). The developed approach could be used as a rapid, accurate and low-cost method to predict yield
for stakeholder farms all over the world where ground data is scarce.
Predicting wheat yield gap and its determinants combining remote sensing, machine learning, and survey approaches in rainfed Mediterranean regions of Morocco
Author(s): Devkota, Krishna; Bouasria, Abdelkrim; Devkota Wasti, Mina; Nangia, Vinay (Elsevier, 2024-08-01)
Date: 2024-05-14
Type: Journal Article
Status: Timeless limited access
Wheat plays a crucial role in Morocco’s food security, economic stability, and livelihoods of farming communities. Assessing key vegetation indices (as yield predictors), along with understanding potential yield, yield gap, and major determinants for this gap at regional and national scales, is vital for improving food security with resilience in variable climatic conditions. Analysing the yield gap and its causes during drought and optimal weather conditions can reduce crop failure risks and enhance productivity specially in variable rainfed production systems. This study aimed to develop scalable methodology to predict field- and landscape-level yield and yield gaps for wheat and their underlying causes examplifying Morocco’s rainfed production environment combining remote sensing, machine learning, and ground information. By analysing six vegetation indices (EVI2, CGVI, MSR, NDVI, OSAVI, and RVI) derived from Sentinel-2 satellite imagery (10 m resolution) over three successive growing seasons (2018–2019, 2019–2020, and 2020–2021), the study employed advanced vegetation index models for accurate prediction of wheat yields and yield gaps at plot and on a larger regional scale within the Rabat-Sale-Kenitra region. To identify the determinants of yield gap, climate and soil datasets were merged with crop management information and the random forest model was fine-tuned and assessed for each season and cumulatively. The findings highlighted that RVI, GCVI, and NDVI vegetation indices were particularly effective in predicting wheat yields, showing the highest R2 and the lowest prediction errors (RMSE). Such predictive methodologies are crucial for policymakers to proactively plan and mitigate risk minimization and adaption plans at regional and national levels. The models predicted rainfed potential yields of 5.99, 1.53, and 4.66 t ha−1, with corresponding yield gap of 3.38, 0.73, and 1.58 t ha−1 for the seasons of 2018/2019 (favorable); 2019/2020 (drought) and 2020/2021 (favorable), respectively. Across three periods, critical factors determining yield include soil moisture, total rainfall during the crop growing period, evapotranspiration, and soil texture and carbon content. To minimize drought risks and maximize benefits during variable rainfall conditions, it is essential to implement pre-season drought forecasts, customize seeding dates based on soil moisture, adopt technologies that enhance soil moisture retention, and utilize climate-adapted farming practices in the semi-arid and arid rainfed regions.
Unveiling the Synergistic Effects of Phosphorus Fertilization and Organic Amendments on Red Pepper Growth, Productivity and Physio-Biochemical Response under SalineWater Irrigation and Climate-Arid Stresses
Author(s): Bouras, Hamza; Devkota, Krishna; Mamassi, Achraf; Loudari, Aicha; Choukr- Allah, Redouane; El-Jarroudi, Moussa (MDPI, 2024-04-26)
Date: 2024-04-26
Type: Journal Article
Status: Open access
In regions facing water scarcity and soil salinity, mitigating these abiotic stresses is paramount for sustaining crop production. This study aimed to unravel the synergistic effects of organic matter and phosphorus management in reducing the adverse effect of saline water for irrigation on red pepper (Capsicum annuum L.) production, fruit quality, plant physiology, and stress tolerance indicators. The study was carried out in the arid Tadla region of Morocco and involved two key experiments: (i) a field experiment during the 2019 growing season, where red pepper plants were subjected to varying phosphorus fertilizer rates (120, 140, and 170 kg of P2O5.ha−1) and saline water irrigation levels (0.7; 1.5; 3; and 5 dS.m−1); and (ii) a controlled pot experiment in 2021 for examining the interaction of saline water irrigation levels (EC values of 0.7, 2, 5, and 9 dS.m−1), phosphorus rates (30, 36, and 42 kg of P2O5.ha−1), and the amount of organic matter (4, 8, 12, and 16 t.ha−1). The field study highlighted that saline irrigation significantly affected red pepper yields and fruit size, although phosphorus fertilization helped enhance productivity. Additionally, biochemical markers of stress tolerance, such as proline and glycine betaine, along with stomatal conductance, were impacted by increasing salinity levels. The pot experiment showed that combining organic amendments and phosphorus improved soil properties and stimulated red pepper growth and root weight across all salinity levels. The integration of phosphorus fertilization and organic amendments proved instrumental for counteracting salinity-induced constraints on red pepper growth and yield. Nonetheless, caution is necessary as high salinity can still negatively impact red pepper productivity, necessitating the establishment of an irrigation water salinity threshold, set at 5 dS.m−1.
Aphanothece sp. as promising biostimulant to alleviate heavy metals stress in Solanum lycopersicum L. by enhancing physiological, biochemical, and metabolic responses
Author(s): Fal, Soufiane; Aasfar, Abderrahim; Ouhssain, Ali; Choukri, Hasnae; Smouni, Abelaziz; El Arroussi, Hicham (Nature Research (part of Springer Nature) (Fully open access journals), 2023-04-27)
Date: 2023-04-27
Type: Journal Article
Status: Open access
Heavy metals (H.M) are a major environmental concern around the world. They have harmful impact on plant productivity and pose a serious risk to humans and animals health. In the present study, we investigated the effect of Aphanothece crude extract (ACE) on physiological, biochemical, and metabolic responses of tomato plant exposed to 2 mM Pb and Cd. The results showed a significant reduction of tomato plant weights and perturbation in nutrients absorption under 2 mM Pb and Cd conditions. Moreover, ACE treatment showed a significant enhancement of plant biomass compared to plants under Pb and Cd. On the other hand, ACE application favoured H.M accumulation in root and inhibited their translocation to shoot. In addition, ACE treatment significantly enhanced several stress responses in plant under Pb and Cd stress such as scavenging enzymes and molecules: POD, CAT, SOD, proline, and polyphenols etc. Furthermore, ACE treatment showed remodulation of metabolic pathways related to plant tolerance such as wax construction mechanism, particularly SFA, UFA, VLFA, alkanes, alkenes, and sterols biosynthesis to enhance tolerance and resistance to H.M stress. In the present study, we emphasized that ACE alleviates H.M stress by minimizing metal translocation to above-part of plant and enhancing plant growth, nutrients absorption, and biochemical responses.
Impact of Terminal Heat and Combined Heat-Drought Stress on Plant Growth, Yield, Grain Size, and Nutritional Quality in Chickpea (Cicer arietinum L.)
Date: 2023-10-30
Type: Journal Article
Status: Open access
Chickpea is the third most consumed pulse and provides a kit of essential nutrients for an exponential population. High temperatures and drought stress are two major abiotic stresses that cause serious effects on chickpea growth and development. The comprehension of abiotic stresses’ impact on chickpea productivity and nutritional quality will permit the selection of promising genotypes. The current study aimed to assess the impact of heat and drought stresses on plant growth, grain yield and its components, grain size, and nutritional quality in chickpea. For this purpose, 43 international chickpea genotypes were evaluated under normal, heat, and combined heat-drought stress conditions. The findings revealed a significant decrease of over 50% in plant height, biological yield, and seed yield under both stress conditions. Grain size and hundred-seed weight were the most heritable traits under normal, heat, and combined heat-drought stress. Proteins were accumulated under both stresses, evolving from 20.26% for normal conditions to 22.19% for heat stress and to 21.94% for combined heat-drought stress. For minerals, significant variation between treatments was observed for Mn, Mg, and Na. Our results also showed a significant impact of genotype and genotype-environment interaction factors only on K content. Using selection indices, 22 genotypes were identified as highly tolerant to the combined heat-drought stress, while eleven genotypes were heat-tolerant. Mineral profile analysis according to the contrasting tolerance clusters revealed decreased potassium content in susceptible genotypes, indicating genetic potential in the studied chickpea collection, ensuring tolerance to both stresses while maintaining good grain quality.