Agricultural Engineering International (E-Journal, CIGR - International Commission of Agricultural Engineering)
Not a member yet
1914 research outputs found
Sort by
Predictive Modeling of Crop Yields: A Comparative Analysis of Regression Techniques for Agricultural Yield Prediction
Full text linkCrop yield prediction plays a key role in modern agriculture, it enables farmers to make decisions about resource distribution, crop production management, and marketing business strategies. Regression models are extensively used for crop yield prediction. The performance of different regression techniques may vary depending on various factors such as the dataset, features, and modeling assumptions. In this paper, Author conducted a comparative study to evaluate and compare the performance of different regression models for agriculture crop yield prediction. Collected a comprehensive dataset encompassing historical crop yield data, weather parameters and pesticides data features from various agricultural regions, then applied and compared various regression models, including LR, KNR, SVR, DTR, RFR, GBR, Linear Model Lasso Regressor, Elasticnet Regressor, Ridge Regressor to predict crop yields for various crops. This study involved evaluating the performance of these regression models based on several performance metrics, including R² score, RMSE, MSE, MAE, Median AE, Explain variance score and computing time. The results of our study provide insights into the comparative performance of different regression models for crop yield prediction in agriculture. Determined that the performance of the regression models vary crop type, area, and dataset used. Overall, The random forest regression model demonstrated the best performance in terms of R2, followed by K neigherst with hyper parameter tunning and decision tree regression. However, the choice of the most suitable regression model may also depend on other factors such as the interpretability and computational efficiency requirements of the application. Our research findings contribute to the existing literature on crop yield prediction in agriculture and afford treasured information for farmers, policymakers, and researchers to make conversant conclusions about the selection of appropriate regression models for crop yield prediction in their specific contexts.
Further research could explore the combination of different regression models or the integration of other ML techniques to better the R2 and robustness of crop yield prediction models in agriculture
Modelling temperature and slice thickness effect on b-carotene, carbohydrate and moisture contents of orange-fleshed sweet potato flour
Full text linkIn this study, the effect of oven temperature (OT) and slice thickness (ST) of orange-fleshed sweet potato (OFSP) on Beta-carotene, carbohydrate, and moisture contents of OFSP flour was determined. A 22 full factorial experimental design with two replications was used. The washed, peeled and sliced OFSP roots were dried to constant weights in an oven. The dried slices were milled into flour using a grinder and then sieved using a 200 µm sieve to achieve particle size uniformity. The colour parameters, carbohydrate, and moisture contents of the resultant flour were determined. Statistical analyses were done using Design Expert 12 software at (p < 0.05) significance level. Results showed that OT had significantly negative effect while ST had significantly positive effect on the pigments, carbohydrate, and moisture contents of OFSP flour. Both OT and ST, however, had significantly positive interaction effect on the dependent variables. At the design points and their proximities, the following linear equations were found to be adequate: B-carotene (b*) = 82.47 - 1.06 * OT - 1.25 * ST + 0.03 * OT * ST; Carbohydrate = 103.87 - 0.55 * OT - 1.27 * ST + 0.02 * OT * ST; Moisture content = 13.87 - 0.07 * OT - 0.11 * ST. However, at the centres of the design space, the linear equations were found inadequate for predictions, which indicated the need for further studies on quadratic or cubic model development. The results mean that 10 mm thick slices oven-dried at 85o C would give properly dried (9.4% M.C.) high-protein (6.7%) flour; while 10 mm thick slices dried at 45o C would give high carbohydrate (76%) flour with good colour retention.
In this study, the effect of oven temperature (OT) and slice thickness (ST) of orange-fleshed sweet potato (OFSP) on Beta-carotene, carbohydrate, and moisture contents of OFSP flour was determined. A 22 full factorial experimental design with two replications was used. The washed, peeled and sliced OFSP roots were dried to constant weights in an oven. The dried slices were milled into flour using a grinder and then sieved using a 200 µm sieve to achieve particle size uniformity. The colour parameters, carbohydrate, and moisture contents of the resultant flour were determined. Statistical analyses were done using Design Expert 12 software at (p < 0.05) significance level. Results showed that OT had significantly negative effect while ST had significantly positive effect on the pigments, carbohydrate, and moisture contents of OFSP flour. Both OT and ST, however, had significantly positive interaction effect on the dependent variables. At the design points and their proximities, the following linear equations were found to be adequate: B-carotene (b*) = 82.47 - 1.06 * OT - 1.25 * ST + 0.03 * OT * ST; Carbohydrate = 103.87 - 0.55 * OT - 1.27 * ST + 0.02 * OT * ST; Moisture content = 13.87 - 0.07 * OT - 0.11 * ST. However, at the centres of the design space, the linear equations were found inadequate for predictions, which indicated the need for further studies on quadratic or cubic model development. The results mean that 10 mm thick slices oven-dried at 85o C would give properly dried (9.4% M.C.) high-protein (6.7%) flour; while 10 mm thick slices dried at 45o C would give high carbohydrate (76%) flour with good colour retention
Simulation of managed aquifer recharge: prospects for recycling treated wastewater in Nigeria: Simulation of managed aquifer recharge: prospects for recycling treated wastewater in Nigeria
No full textThe study evaluated the potential of recycling treated industrial effluent for groundwater quality and quantity restoration using a laboratory–scale Soil Aquifer Treatment (SAT) simulator. SAT has the potential of reverse groundwater level decline being experienced in the Northeastern part of Nigeria and saltwater intrusion and groundwater quality deterioration in the coastal zones of the country. Soil Column Depth (SDC) and Hydraulic Loading Rate (HLR) were optimized for the best treatment performance. Results show that HLR of 14.6 mm/min at an SCD of 1.5 m gave maximum removal efficiency for all parameters (hydrogen ion concentration (pH), Temperature, Electrical Conductivity (EC), Total Dissolved Solids (TDS), Total Suspended Solids (TSS), Dissolved Oxygen (DO), Bio-chemical Oxygen Demand (BOD5), Total Hardness (TH), Chloride (Cl¯), Calcium (Ca2+), Magnesium (Mg2+), Sodium (Na+), Potassium (K+) and Bacterial Count (BC)) tested in comparison with HLR 16.98 and 20.37 mm/min and SCD of 0.5 and 1.0 m.; This can be attributed to longer contact time in the soil column. Further evaluation of the results from the study indicates that surface spreading is best suited for the Sudan and Sahel Savannah areas of the country. In contrast, direct injection into wells is best suited for the southern and coastal areas. Given that Nigeria has a vast potential for Managed Aquifer Recharge (MAR), the implication is that the implementation requires policy and regulatory frameworks to enable bulk wastewater producers to put their effluents to positive use and thus to enhance environmental sustainability
DEVELOPMENT OF AN AUTOMATIC VARIABLE RATE SPRAYING SYSTEM BASED ON CANOPY CHARACTERIZATION USING ARTIFICIAL INTELLIGENCE
No full textSpraying on tree crops must consider the canopy's structural features to maximize its effectiveness. The main drawbacks to VRI technology include the complexity of successfully implementing it and the lack of evidence that it assures better performance in net profit or water savings. Hence, a novel framework based on canopy characterization was presented in this research for an automatic variable-rate spraying system. The first phase was collecting the data, and the next was cleaning it to eliminate redundant information. The pre-treated data are then entered into the Crest- Stride-wise Regression Framework we devised, where we extract the canopy features and evaluate additional parameters. In addition, our proposed model automatically predicts the nozzle's flow rate and pressure based on a threshold value. Thus, this research shows that the recommended strategy achieves 99.98% accuracy, 99.99% precision, 99.99% F1 score, and 99.99% recall. As a result, our study enables safer and more efficient spraying distribution in the agricultural sector
Physical characterisation and development of mass and volume models for tannia (Xanthosoma sagittifolium) cormels: Physical characterisation and mass and volume models for tannia cormels
No full textPhysical properties of agricultural products are important for proper mechanization of their processing and handling operations. Models established based on these physical properties can also help in systems automation and ensure efficient processing. This study determined some physical characteristics of tannia cormel and developed mathematical models for estimating its mass and volume using its geometrical attributes. Linear dimensions were within the range 20.87-168.30 mm while the projected areas were within the range 4.63-207.72 cm2. Average mass, volume and density were within ranges 7.40-256.80 g, 7.00-215.00 cm3 and 947.37-1565.45 kg/m3 respectively. Average sphericity, aspect ratio, shape index, eccentricity and elongation ratio were 0.73, 0.60, 1.84, 0.76 and 1.81 respectively. The results showed that tannia cormels are closer to being prolate spheroid in shape with relatively high sphericity. The results showed that mass and volume of tacca cormel can be reliably predicted using its projected areas and volume (for mass modelling only). The most suitable of all the models was obtained for mass model with respect to volume (R2 = 0.976). Data provided in this study are useful in the development of postharvest handling and processing systems for tannia cormels
Impact of Ranbir Canal Closure on Wheat Productivity in Jammu District
Full text linkThe aim of the study was to assess the impact of the Ranbir canal closure on wheat productivity which is closed for de-siltation and cleaning purpose for the period of January to Mid-April every year. The study involved the use of pre-tested proforma and the data regarding the effect of Ranbir canal closure on wheat was collected by a recall method from the farmers of three villages namely Kalyanpur, Rambagh and Musa chak of Jammu district in the union territory of Jammu and Kashmir. The results revealed that with the closure of Ranbir canal the total loss in productivity due deficiency in irrigation was to the tune of 13% which accounted for ₹ 19 crore for the whole Ranbir command. The study emphasis that the government and policy makers should take major steps in solving the problem to stop hue and cry of Jammu farmers and more importantly to restrict the annual loss of ₹ 19 crore rupees due to the closure of the canal
LIME RATES AND METHODS OF APPLICATION FOR SOYBEANS GREW IN A SANDY LATOSOL
Full text linkSoil acidity correction aims to neutralize Al3+ and H+ and supply Ca and Mg for the development of crops, such as soybean. However, there is no consensus on the optimum lime rates and application methods for sandy soils, especially in no-till, given their increased susceptibility to leaching of water and nutrients as well as reduced capacity of soil colloids. Thus, the aim of this study was to compare the efficiency of lime rates and application methods and establish liming criteria for soybean production in a sandy Latosol in Northwestern Paraná. The experimental soil was a typical dystrophic Red Latosol of sandy texture. Treatments consisted of surface and incorporated application of lime to achieve 50, 60, 70, and 80% base saturation and an untreated control (without lime). Soybean was grown in undeformed soil columns. After 114 days, plants were evaluated for height, stem diameter, shoot fresh weight, and shoot dry weight. The soil was analyzed for pH H2O, pH CaCl2, Al3+, exchangeable calcium, exchangeable magnesium, available phosphorus and potassium. The liming criteria that resulted in maximum development of soybean crops in sandy soil were base saturation of 60%, pH H2O of 6.1, 3.20 cmolc kg−1 calcium, and 1.89 cmolc kg−1 magnesium
On the water desorption of fruits: a case study of watermelon (Citrullus Lanatus)
Full text linkStudies on drying of the Watermelon seeds or rinds are available, but not on drying of the fruit flesh. Data on the sorption of Watermelon fruit (Citrullus Lanatus), which are useful and important when identifying optimal food drying and storage conditions, are also not available. Therefore, the main goal of this study is to investigate the desorption behavior of Watermelon using the dynamic method requiring the automated Dynamic Vapor Sorption (DVS) technique based on a humidity-generating device. The moisture desorption isotherms are determined at three different temperatures (20, 30 and 40°C) over a relative humidity range of 0-80%. In addition, 11 different models are applied to the experimental data in order to select the appropriate desorption curve equation. The models are compared using the correlation coefficient, the coefficient of determination, the standard error, the reduced chi-squared, the mean bias error and the root mean square error; they are predicted by a non-linear regression analysis using the Curve Expert software and MS Excel computer program. The effect of the temperature on the constants of the found equation is also examined. Besides, the desorption isosteric heat of Watermelon is determined using the Clausius-Clapeyron relation. Contrary to long times taken in the static method, the results show that 4.5 days are widely sufficient to reach the equilibrium via the DVS device. In addition, the obtained curves are of the type III and the Henderson model best fits the experimental data. In the interval 0.05-0.45 kg water.kg dry matter-1 of equilibrium moisture, the values of the isosteric heat vary from 65.02 to 113.25 kJ mol-1. Finally, the equation giving the isosteric heat of desorption v.s. the equilibrium moisture content is obtained
Design and experimentation of a corn pericarp peeling machine
Full text linkLa presente invención se relaciona con un nuevo proceso de producción de maíz quebrado nixtamalizado deshidratado, sin producción de nexayote y cuya molienda da por resultado una masa que tiene cualidades mejoradas, pudiendo ser conservado el producto durante meses. La ventaja de este proceso y equipo con respecto de los del estado de la técnica es que logra un producto con cualidades organolépticas mejoradas y con características reológicas de la masa que resulte de su molienda, mejoradas. La invención tiene dos vertientes, un proceso y un equipo. El proceso se caracteriza porque el quebrado se lleva a cabo para obtener un tamaño de partícula entre 4 y 4.5 milímetros, la nixtamalización se lleva a cabo con el maíz quebrado en un reactor de nixtamalización giratorio, con agua en una proporción de 0.5 a 1.0 con respecto a la cantidad de maíz y con cal en una proporción 6 y 15 kg por tonelada de maíz; la temperatura de nixtamalización ubicada entre 60 y 100° C y durante 25 a 45 minutos, con el reactor girando; el secado del grano quebrado nixtamalizado se lleva a cabo haciendo circular a contracorriente, por entre las fracciones del nixtamal aire en condiciones ambientales
Development of a Solar-Powered Device for Bloodworm Control in Rice Fields
Full text linkThe aim of this research is to develop a solar-powered device to control the bloodworm Chironomus spp. in rice fields instead of using harmful chemical pesticides. The developed control device uses clean solar energy and helps to protect the environment from pesticide pollution residuals. The newly developed control device generates a continuous high-voltage electrocution current below the subsoil surface to eliminate adult bloodworms and larvae. The device is provided with a fully automated electronic control circuit, an electrocution generator, and a group of electrodes. The bloodworm infection decreased the quantity and quality of rice yield. Three factors were examined to assess the efficacy of the bloodworm control device. Four electrocution potential levels (8, 12, 16, and 20 kV) were tested. Additionally, three electrode depth levels (60, 120, and 180 mm) were examined with three operating periods (10, 20, and 30 minutes). The results showed high significance in reducing the bloodworm population using the prototype compared to the chemical insecticide control treatment using Furadan (Carbofuran) 10% granular. The reduction rate in bloodworms reached 90.92% and 91.94% in adult bloodworms and larvae, respectively, at the highest levels of the tested variables. The operating cost for the device ranged from 25 to 40 USD ha-1, while the consumed energy ranged from 40 to 100 kWh ha-1. The use of the solar-powered control device is effective in eliminating adult bloodworms and their larvae in a short time. Therefore, it is recommended to use the solar-powered control device to eliminate the bloodworm in rice fields