Evaluating the Potentials of PLSR and SVR Models for Soil Properties Prediction Using Field Imaging,Laboratory VNIR Spectroscopy and Their Combination

Pedo-spectroscopy has the potential to provide valuable information about soil physical,chemical,and biological properties.Nowadays,wemay predict soil properties usingVNIRfield imaging spectra(IS)such as Prisma satellite data or laboratory spectra(LS).The primary goal of this study is to investigate machine learning models namely Partial Least Squares Regression(PLSR)and Support Vector Regression(SVR)for the prediction of several soil properties,including clay,sand,silt,organic matter,nitrate NO3-,and calcium carbonate CaCO_(3),using five VNIR spectra dataset combinations(%IS,%LS)as follows:C1(0%IS,100%LS),C2(20%IS,80%LS),C3(50%IS,50%LS),C4(80%IS,20%LS)and C5(100%IS,0%LS).Soil samples were collected at bare soils and at the upper(0–30 cm)layer.The data set has been split into a training dataset 80%of the collected data(n=248)and a validation dataset 20%of the collected data(n=61).The proposed PLSR and SVR models were trained then tested for each dataset combination.According to our results,SVR outperforms PLSR for both:C1(0%IS,100%LS)and C5(100%IS,0%LS).For Soil Organic Matter(SOM)prediction,it achieves(R^(2)=0.79%,RMSE=1.42%)and(R^(2)=0.76%,RMSE=1.3%),respectively.The data fusion has improved the soil property prediction.The highest improvement was obtained for the SOM property(R^(2)=0.80%,RMSE=1.39)when using the SVR model and applying the second Combination C2(20% of IS and 80%LS).

Impact Assessment of Technology Change on Durum Wheat Productivity： A Cross Sectional Analysis in Central Semi-arid Tunisia

The enhancement of wheat yield in Tunisia becomes a must for policy makers who need to reduce the importations of this commodity. In this context, the ＂Food Security in Arab Countries＂ project has been established in order to transfer technological innovations that improve irrigated wheat productivity. As a pilot area, this project is being implemented in Chebika （Central Tunisia） region, where in the last two years a new technological package of durum wheat production has been tested by many farmers of the region. The objective of this study is to identify the sources of output gains between farmers participating in the project trials and farmer＇s using conventional techniques. Tornqvist-Thiel index was used for the identification of the output gains generated by the technology package. Data used for the analysis were collected from 60 participating farmers during 2011-2012 cropping season, and 110 non-participating farmers. Results show that average production value differential between participating and non-participating farmers is 48.4%. This value is composed of 9.3% gain generated from global factor productivity and 39.1% from the increase of the inputs use. It also indicates the relative importance of inputs contributing to the global factor productivity difference between enhanced technological package and conventional practices in the region. These results are valuable for policy makers since they can be used to focus on main factors affecting the improvement of irrigated wheat productivity in Central Tunisia. Encouraging the adoption of the new technological package is then highly recommended.

Poverty and Agroforestry Adoption： The Cases of Mucuna pruriens and Acacia auriculiformis in Godohou Village （Southern Benin）

The decomposition of the environmental degradation cost in Benin Republic revealed that the agricultural activities are responsible of the greatest amount of this cost （76.1%）. This situation is strengthened by the fallow periods shortening （and even suppression） in the southern Benin in general, because of demographic pressure. The promotion of some improved fallow technologies （IFT） was then launched some decades ago. This study focused on two IFT of high agro-ecological value, Mucuna pruriens and Acacia auriculiformis, in order to determine the influence of the farmers＇ wellbeing state on their farming systems in general, and on the adoption level of these two technologies in Godohou village （southern Benin）. The data analysis revealed that： There was no significant difference between the farmers＇ amount knowing the agronomic and ecological value of Mucuna pruriens and Acacia auriculiformis from a level of prosperity to another; Three wealth levels were distinguished： The poor class （Ayatonon class）, the less poor class （Metchivo-Houedeka class） and the non poor class （Hotonon class） which represented respectively 35.4%, 55.9% and 8.7%;The adoption rate of Mucuna and Acacia fallow was globally low in Godohou village （25.7%）, but this adoption rate was lesser in the poorest class than in all other classes. This trend was confirmed if we integrate a global agro-ecological analysis of the farming systems practiced by the farmers.

Single Layer Centrifugation with Androcoll-E^(TM) improved progressive motility and percentage of live spermatozoa with intact acrosome of chilled stallion semen but did not have an effect on DNA integrity

A significant number of stallions produce low quality ejaculates with high sensibility to chilling. Single Layer Centrifugation (SLC) with Andro-coll-ETM has been presented as an efficient method of selecting good quality spermatozoa. In the current study, changes in sperm quality (motility, viability, acrosome integrity and DNA damage) occurring during storage at 5?C for a maximum of 72 h, were investigated. For that, one ejaculate from 12 stallions was split in two aliquots: control and SLC-selected. Both aliquots were chilled and stored at 5?C and spermatozoa were evaluated for motility, viability and acrosome integrity at 24, 48 and 72 h post collection. DNA damage was evaluated at 48 h post collection using the comet assay. In the SLC-selected aliquots, there was a significant improvement in terms of progressive motility (0 h: P = 0.005;24 h: P 0.05). SLC with Androcoll-ETM improved semen quality prolonging sperm longevity of chilled semen (P = 0.012). This positive effect was more evident in ejaculates most sensitive to chilling that had a sharp decrease in motility in the first 24 h of refrigeration and for all ejaculates at 72 h post-chilling. Therefore, this method reveals to be a useful technique for selecting spermatozoa and maintain sperm quality during storage.

Small ruminant value chain in Al-Ruwaished District,Jordan

This study aims to assess the small ruminant value chain in Al-Ruwaished District,Jordan,to identify the potential intervention areas that could improve the production efficiency and guarantee the sustainability of the small ruminant sector in this area.Sheep breeding is the source of livelihood for most of the people in Al-Ruwaished District,which is characterized by the large number of sheep and goats.We surveyed 5.0% of the small ruminant holders in the study area and conducted individual interviews and surveys with the potential actors in the value chain to undertake a small ruminant value chain analysis.From the survey,we found that the small ruminant value chain consists of five core functions,namely,input supply,production management,marketing,processing,and consumption.Despite the stable impression given by the large number of holdings in the small ruminant sector,the surveyed results show a clear fragility in the value chain of small ruminants in this area.The small ruminant production system is negatively impacted by climate change,especially continuous drought.In addition,the high prices of feed that the farmer cannot afford with clear and real absence of the governmental and non-governmental support activities also impact the development of the value chain.The results of strengths,weaknesses,opportunities,and threats(SWOT)analysis reveal that the major constraints faced by this value chain could be divided into external and internal threats.Specifically,the most prominent external threats are the nature of the desert land and continuous drought,while the major internal threats are the absence of appropriate infrastructure,shortage of inputs,and weakness in the production management and marketing.We proposed solutions to these challenges to ensure the sustainability and effectiveness of the sector,such as the formulation of emergency response plans to severe weather,qualifying farmers’skills,and establishment of agricultural cooperative societies.

A method to estimate aquifer artificial recharge from a hill dam in Tunisia

in arid and semi-arid areas, artificial recharge is a key technology in groundwater resources management, and a reliable estimate of artificial recharge is necessary to its sustainable development. Several methods are available to estimate the artificial recharge; however, most of them require field data or model parameters, thus limiting their applications. To overcome this limitation, we presented an analytical method to estimate the artificial recharge through monitoring the water release by piezometer and analysing the controlling factors of the artificial recharge from a hill dam in Tunisia. A total of 97 measurements of water flow in the streambed recorded from 4 gauging stations were analysed. Results indicated that the average infiltration velocity ranged from 0.043 to 0.127 m/d and the infiltration index varied from 7.6 to 11.8 L/（s.km）. Pearson＇s correlation coefficient analysis shows that the infiltration index, the stream gradient, the thickness of unsaturated zone, the number of infiltration pond, the stream geometry, and the water flow rate were found to be the main factors in determining the infiltration. The high correlation coefficients （0.908 for the number of infiltration pond and 0.999 for the stream geometry） mean that the number of infiltration pond and the stream geometry are the most influential factors. Time variations of groundwater level were used to analyze the recharge effects on the piezometry of aquifer. The analysis showed that during the artificial recharge, the water table increased at a rate of 5 mm/d and that the increase was limited to the area surrounding the recharge site. Based on the results of the study, building infiltration ponds along streambed and improving the potential of rainwater harvesting over the study area are recommended.

Front-Face Fluorescence Using UV-LED Coupled to USB Spectrometer to Discriminate between Virgin Olive Oil from Two Cultivars

A simple setup using a 365 nm LED coupled to a USB spectrometer through an optical fibre, in a front-face fluorescence configuration, was used to investigate the ability of fluorescence spectroscopy technique to discriminate between varieties of olive oil. To achieve this task, Virgin Olive Oils (VOO) from two major Tunisian olive cultivars known as Chetoui and Chemlali were used. Spectral analysis showed a clear separation between these two VOO varieties. A one-way ANOVA attests that this discrimination is significant. The Principal Components Analyses (PCA) showed that the normalized fluorescence intensities are the good parameters for this discrimination. This observation strengthens the potential of our spectral parameters to perform reliable analysis.

Growth, Development and Suitability for Kent of Mango Rootstocks on Soil Substrates Collected under <i>Anacardium occidentale</i>L., <i>Khaya senegalensis</i>(Desv.) A. Juss and <i>Mangifera indica</i>L., in Casamance, Senegal

With an overall contribution of nearly 4 billion CFA francs to Senegal’s income, providing 23,000 employments more than 50% are women in 2021, the mango sector has shown its importance in the Senegalese economy even if the potential remains largely under-exploited. Thus, the study on the main local varieties remains an important perspective. This work carried out in the farm of the agroforestry department concerns the growth and development of four varieties (Pince, Kouloubadaseky, Sierra Leone and Diourou) on different soils (Mangifera indica, Anacardium occidentale and Khaya senegalensis). This work aims to contribute to the knowledge of the most cultivated varieties in Casamance. It is also a question of seeing the response of these varieties to grafting with the Kent variety. An experiment was conducted for one year with a split plot design consisting of 4 replicates (blocks). Each block contains 4 plots and each plot contains 3 sub-plots with 20 plants each. The parameters measured were: diameter at the collar, height, number of leaves, biomass, number of growth units and grafting success rate. The Sierra Leone variety showed the best growth results in terms of diameter at the crown (0.511 ± 0.090), leaf production (16 ± 2.52) and dry biomass (28.67 ± 16.80). The Kouloubadaseky variety had the best height record (41.90 ± 6.15) and the Diourou variety gave the best results in terms of fresh biomass (68.94 ± 30.90), number of growth units (9.350 ± 2.06) and grafting success rate (78.84% ± 29.44%). Anacardium occidentale soil substrate gave the best growth in height (39.73 ± 5.54 cm) while the substrate collected under M. indica L produced a greater number of leaves (13.14 ± 3.64) and grafting success rate (71.12% ± 37.25%). The Khaya senegalensis substrate recorded the highest values in biomass production (61.00 ± 35.93 for fresh biomass and 25.25% ± 15.74% for dry biomass).