Optimum Crop Yield Research Articles

A comparison of soil liming requirement methodologies in temperate, Northern European pedo‐climates

AbstractBackgroundLiming agricultural land is essential to optimise crop yield and soil nutrients. Despite the importance of pH management in agricultural soils, liming applications have been decreasing in the United Kingdom for decades. There is no comparison of contemporary and historical liming requirement (LR) methods for Northern European, temperate climate mineral soils high in organic matter (OM).AimsThe aims of this research were to thoroughly comparatively analyse current methodologies and to ascertain which soil characteristics contribute to LR reactions.MethodsAnalysis compared methods for determining liming values common in the United Kingdom (Scottish Agricultural College [SAC] look‐up chart, RothLime model), Europe and the United States (Shoemaker–McLean–Pratt, Sikora, Modified Mehlich buffers), and the 30‐min calcium hydroxide titration developed by the University of Georgia.ResultsRothLime and SAC highly underestimated the LR value in acidic soils. The buffers highly over or underestimated LRs. The UGA titration method is a cheap, easy and accurate method which could be utilised for high OM soils but requires further calculation development. The characteristics most associated with soil–lime reactions in this experiment were measures of exchangeability (cation exchange capacity and loss on ignition, and by proxy, lime buffering capacity).ConclusionsThere is an opportunity to create buffer calculators and titration equations adapted to high OM soils. These are suggested for further development, through a larger diversity of UK soil types grouped by buffering capacity ranges. Including soil exchangeability factors in lime management calculations may contribute to more accurate values and therefore better resource management. Increasing LR accuracy for site‐specific soil pH management, used in precision agriculture technologies, is a necessary tool for the conservation of natural resources like limestone, managing resource use efficiency, and for optimising yields.

Toward automated irrigation management with integrated crop water stress index and spatial soil water balance

AbstractDecision support systems intended for precision irrigation aim at reducing irrigation applications while optimizing crop yield to achieve maximum crop water productivity (CWP). These systems incorporate on-site sensor data, remote sensing inputs, and advanced algorithms with spatial and temporal characteristics to compute precise crop water needs. The availability of variable rate irrigation (VRI) systems enables irrigation applications at a sub-field scale. The combination of an appropriate VRI system along with a precise decision support system would be ideal for improved CWP. The objective of this study was to compare and evaluate two decision support systems in terms of seasonal applied irrigation, crop yield, and CWP. This study implemented the Spatial EvapoTranspiration Modeling Interface (SETMI) model and the Irrigation Scheduling Supervisory Control and Data Acquisition (ISSCADA) system for management of a center pivot irrigation system in a 58-ha maize-soybean field during the 2020 and 2021 growing seasons. The irrigation scheduling methods included: ISSCADA plant feedback, ISSCADA hybrid, common practice, and SETMI. These methods were applied at irrigation levels of 0, 50, 100, and 150% of the full irrigation prescribed by the respective irrigation scheduling method. Data from infrared thermometers (IRTs), soil water sensors, weather stations, and satellites were used in the irrigation methods. Mean seasonal irrigation prescribed was different among the irrigation levels and methods for the 2 years. The ISSCADA plant feedback prescribed the least irrigation among the methods for majority of the cases. The common practice prescribed the largest seasonal irrigation depth among the methods for three crop-year cases. The maize yield in rainfed was found to be significantly lower than the irrigated levels in 2020 since 2020 was a dry year. No significant differences were observed in crop yield among the different irrigation methods for both years. The CWP among the different irrigation methods ranged between 2.72 and 3.15 kg m−3 for 2020 maize, 1.03 and 1.13 kg m−3 for 2020 soybean, 3.57 and 4.24 kg m−3 for 2021 maize, and 1.19 and 1.48 kg m−3 for 2021 soybean. Deficit level (50%) had the largest irrigation water productivity in all crop-year cases in this study. The ISSCADA and SETMI systems were found to reduce irrigation applications as compared to the common practice while maintaining crop yield. This study was the first to implement the newly developed integrated crop water stress index (iCWSI) thresholds and the ISSCADA system for site-specific irrigation of maize and soybean in Nebraska.

Detection of Unhealthy Citrus Leaves using Deep Neural Network

Abstract: This research paper presents a novel approach for detecting unhealthy citrus leaves using deep neural networks (DNNs). By leveraging convolutional neural networks (CNNs) and a comprehensive dataset of healthy and diseased citrus leaf images, we train a robust model for accurate classification. Data augmentation and transfer learning techniques are employed to enhance the model's performance. Extensive evaluation demonstrates the superiority of our approach. Our automated method contributes to plant health monitoring, facilitating timely interventions and optimizing crop yield for sustainable agriculture

Integrated Nutrient management for optimal plant health and crop yield

In the pursuit of sustainable agriculture and optimal crop yields, Integrated Nutrient Management (INM) has emerged as a comprehensive strategy that integrates organic and inorganic sources of nutrients. This article explores the principles and components of INM, emphasizing its role in fostering plant health, enhancing nutrient use efficiency, and ensuring the long-term sustainability of soil and ecosystems. The key components of INM include the judicious use of organic fertilizers, precision application of inorganic fertilizers, crop rotation, and the integration of beneficial microbial inoculants. The benefits of INM encompass improved nutrient use efficiency, sustainable soil health, environmental sustainability, and enhanced resilience to climate variability. As global agriculture faces the challenges of feeding a growing population while minimizing environmental impact, the adoption of Integrated Nutrient Management stands out as a pivotal strategy for achieving a harmonious balance between productivity and sustainability in modern farming.

Partial substitution of exogenously applied phosphatic fertilizers by phosphate solubilizing bacteria in maize under calcareous soil

Phosphorus (P) availability is the major constrain in obtaining optimum crop yield in calcareous soils due to its precipitation as dicalcium and octacalcium phosphate by reacting with Ca+2and Mg+2. Therefore, we explored the role of phosphate solubilizing bacteria (without and with PSB @ 2 kg ha−1) in optimizing maize yield and P availability from soluble and insoluble P sources applied @ of 100 kg P2O5into calcareous soil. PSB inoculation significantly improved maize plant height (5.6%), 1,000 grain weight (11%), dry matter (7.5%), stover (10.8%) and grain yield (6.8%), plant P concentration (10.1%) and uptake (18.6%), extractable P (3.1%), agronomic (48%) and uptake (53%) P use efficiency over uninoculated plots. Phosphorus application significantly improved maize yield, soil health and agronomic P use efficiency (4.84 times over control); however, its impact was more pronounced when applied as 50% P each from farmyard manure (FYM) and single super phosphate (SSP). On the basis of overall performance, the sources were ranked as 50% FYM + 50% SSP >50% rock phosphate (RP) + 50% SSP > 100% SSP > 75% FYM + 25% SSP > 75% RP +25% SSP > 100% FYM > 100 RP > control. Interactively, a significant and maximum increased over absolute control in most of the soil and plant tested characteristics were observed when 100 kg P2O5ha−1was supplemented 50% each as FYM and SSP along with PSB inoculation which was followed by 50% P each as FYM and SSP demonstrating that PSB were effective in enhancing RP solubilization under calcareous soil. Maximum value cost ratio of 3.1 was observed for 50% P each as FYM and SSP + PSB which was similar to 100% P as FYM + PSB and 75% FYM+ 25% SSP + PSB. Therefore, in calcareous soil P shall be amended 50% each as organic and mineral sources with PSB for its efficient utilization and obtaining optimum yield of maize.

Broadband Measurements of Soil Complex Permittivity.

Agriculture is a major consumer of freshwater and is often associated with low water productivity. To prevent drought, farmers tend to over-irrigate, putting a strain on the ever-depleting groundwater resources. To improve modern agricultural techniques and conserve water, quick and accurate estimates of soil water content (SWC) should be made, and irrigation timed correctly in order to optimize crop yield and water use. In this study, soil samples common to the Maltese Islands having different clay, sand, and silt contents were, primarily, investigated to: (a) deduce whether the dielectric constant can be considered as a viable indicator of the SWC for the soils of Malta; (b) determine how soil compaction affects the dielectric constant measurements; and (c) to create calibration curves to directly relate the dielectric constant and the SWC for two different soil types of low and high density. The measurements, which were carried out in the X-band, were facilitated by an experimental setup comprising a two-port Vector Network Analyzer (VNA) connected to a rectangular waveguide system. From data analysis, it was found that for each soil investigated, the dielectric constant increases notably with an increase in both density and SWC. Our findings are expected to aid in future numerical analysis and simulations aimed at developing low-cost, minimally invasive Microwave (MW) systems for localized SWC sensing, and hence, in agricultural water conservation. However, it should be noted that a statistically significant relationship between soil texture and the dielectric constant could not be determined at this stage.

Optimizing relative root-zone water depletion thresholds to maximize yield and water productivity of winter wheat using AquaCrop

Determination of relative root-zone water depletion (RRWD) thresholds to trigger irrigation is crucial to create optimal irrigation schedules targeting maximum yield and/or water productivity with limited water supply for a crop. In this study, a numerical procedure to determine RRWD thresholds was developed through coupling AquaCrop software with genetic-simplex algorithms. Using a two-year field lysimetric experiment for winter wheat conducted in the North China Plain (NCP), AquaCrop adequately simulated canopy cover, final aboveground biomass, grain yield, seasonal evapotranspiration, and soil water storage, with the normalized root mean squared error (NRMSE) smaller than 15 % and determination coefficient (R2) larger than 0.84. The global optimum range of RRWD thresholds was preliminarily determined using the genetic algorithm, and subsequently final RRWD thresholds were optimized by fine tuning using the simplex algorithm. The RRWD threshold combinations (composed of the RRWD thresholds to trigger different sequential irrigation events) for varying number of irrigation events (i.e.1–4) were optimized based on 39 years of historical meteorological data, and the effects of climate change on the optimal crop yield (Ya, opt), water productivity (WPopt), and the combinations of optimized RRWD threshold (RRWDopt) were investigated. The results indicated that both Ya, opt and WPopt generally increased with time showing a tendency of gradually elevated annual CO2 concentration and seasonal average effective temperature. Irrespective of the number of irrigation events during the winter wheat growing season, the differences of RRWDopt for different combinations of irrigation sequence and event in the same kind of hydrological year were relatively small, with a coefficient of variation consistently less than 23 % and a mean of 8 %. When combinations of mean RRWDopt were applied into AquaCrop to trigger irrigation for winter wheat in various hydrological years, the simulated yield (Ya, sim) and water productivity (WPsim) under 1–4 irrigation events were found to be comparable to their respective optimums (Ya, opt and WPopt), with all the values of Ya, sim (WPsim) falling in the range of 92 %Ya, opt (90 %WPopt). Therefore, the mean RRWDopt should be helpful to formulate rational irrigation management strategies of winter wheat under changing climatic conditions in the NCP.

Optimizing Crop Yield and Reducing Energy Consumption in Greenhouse Control Using PSO-MPC Algorithm

In this study, we present a novel smart greenhouse control algorithm that optimizes crop yield while minimizing energy consumption costs. To achieve this, we relied on both a greenhouse climate model and a greenhouse crop yield model. Our approach involves applying the model predictive control (MPC) method, which utilizes the particle swarm optimization (PSO) algorithm to identify optimal controllable parameters such as heating, lighting, ventilation levels. The objective of the optimization is to maximize crop yield while minimizing energy consumption costs. We demonstrate the superiority of our proposed control algorithm in terms of performance and energy efficiency compared to the traditional control algorithm. The effectiveness of the PSO-based optimization strategy for finding optimal controllable parameters for MPC control is also demonstrated, outperforming the traditional genetic algorithm optimization. This study provides a promising approach to smart greenhouse control with the potential for increasing crop yield while minimizing energy costs.

Forecasting of Optimal Crop Yield through Data Mining Algorithm

The initial stage of analytics is descriptive analytics. It is a method via which we can learn about the past. We are aware that the past serves as the finest indicator of the upcoming. That is study, Descriptive analytics are used by us to estimate crop yields effectively for the production of sugarcane in agriculture. Three datasets—the soil, rainfall, and yield datasets—are used in this paper. In order to determine the real estimated cost and the accuracy of various strategies, we create a composite dataset and then apply a number of supervised techniques to it. Three supervised techniques—crop prediction, provision direction, and LSS method—are employed in this research. It is a comparative study that reveals the mistake rate and accuracy of training the suggested model. The training model should be more accurate and have a lower error rate than possible. Additionally, the suggested model can provide the real cost of the projected crop production and can be classified as LOW, MID, or HIGH.

Seed Science and Technology. Volume 51 Issue 1 (2023)

Seed quality is the basis for differential crop productivity. Seed companies depend on the quality of the seeds for the seed trade, while farmers depend on the quality of the seeds to improve their productivity and secure their livelihood. Germination and varietal identification/purity are fundamental aspects of seed quality that are of prime importance to the global seed trade. Seed germination is influenced by several factors among which are the genetic factors and environmental cues of the prevailing growing conditions where the plant grows. Among these cues, climate change fundamentally affects crop development at all stages, starting from germination and seedling growth, to flowering and fruiting. Several methods have been formulated and validated for the evaluation of the varietal identification/purity for some crops, facilitate synchronised seed germination and enhance uniform field establishment for optimum crop yield in the face of climate change. This issue ofSeed Science and Technologyincludes papers discussing the application of some of the methods, for example, prechilling and the use of exogenous gibberellin to stimulate germination, the use of tetrazolium as a quick viability test for rice seeds, the applied phenol test for varietal identification of rice seeds, and seed priming to enhance germination ofCorethrodendron multijugumseeds. In addition, the physiological response of seed to soil salinity and storage environment conditions are also discussed.

Machine Learning and IoT Applications in Agriculture

Agriculture is an industry that has historically relied on traditional methods for crop production, but with the advent of new technologies, it is now possible to integrate machine learning and Internet of Things (IoT) applications to improve agricultural practices. Machine learning algorithms and IoT devices can be used to analyze data collected from agricultural fields to optimize crop yield, reduce resource consumption, and improve farm management. In this review paper, we explore the various applications of machine learning and IoT in agriculture, specifically focusing on their use in crop monitoring, disease detection, and water management. We examine the challenges associated with implementing these technologies in agriculture, including issues related to data collection, privacy, and security. Finally, we discuss the potential benefits of integrating machine learning and IoT in agriculture and identify future research directions that can help advance this field. Overall, this review highlights the potential of machine learning and IoT technologies to revolutionize agriculture and improve food security in the years to come. The Internet of Things (IoT) network must be integrated with sensors in order for "smart agriculture" to be a reality. At many layers of the IoT system architecture, machine learning (ML) techniques are incorporated to increase usefulness and capabilities. For agricultural systems to properly integrate with information technology, intelligent agricultural systems must be established, and all types of information created by agricultural systems must be integrated and analysed.The agriculture sector might undergo a transformation thanks to the fusion of machine learning (ML) and internet of things (IoT) technology. Precision agriculture and more economical resource usage are made possible by using IoT sensors to collect data on a variety of factors, including soil moisture, temperature, and nutrient levels. Then, using these data, ML algorithms may be used to forecast outcomes and improve decision-making. For example, they can forecast agricultural yields, spot disease or insect infestations, and suggest the best dates for planting and harvesting.

Efficacy of rice husk and halophilic bacterial biofilms in the treatment of saline water.

Water salinity causes less production of agricultural productivity, low economic returns, soil destructions, less sustainability, and reduction in the germination rate. The current study was aimed to understand the combined potential of halophilic bacteria and rice husk in treating water salinity. In total, 10 halophilic bacterial isolates were isolated from Khewra Mines, Pakistan. Bacterial isolates were characterized by biochemical tests. 16S rRNA gene sequencing identified the isolate SO 1 as Bacillus safensis (accession number ON203008) being the promising halophilic bacteria tolerating upto 3 M NaCl concentration. Next, rice husk was used as carbon source for bacterial biofilm formation, growth and propagation. For saline water treatment, the experimental setting comprising glass wool, rice husk and artificial sea water (3 M) was set. B. safensis biofilm was developed in test samples to desaline the saline water containing 3 M NaCl concentration. Following NaCl decline, flame photometric analysis was used to check the desalination extent of treated saline water. Results showed decreased sodium level in sea water in the presence of rice husk and glass wool. The eluted water used for the germination of Zea mays seeds showed improved growth performance. Also, decreased photosynthetic pigments (chlorophyll "a" = 18.99, and chlorophyll "b" = 10.65), sugar contents (0.7593), and increased carotenoid (1526.91), protein contents (0.4521) were noted compared to control. This eco-friendly approach for bioremediation of salt-affected soils to optimize crop yields under stress through halophilic bacteria and rice husk may overcome the problem of the reduced yield of cash crops/agriculture and water shortage by salinity.

Effects of acidifiers on soil greenhouse gas emissions in calcareous soils in a semi-arid area

In most agricultural fields, when soil pH is high, elemental sulfur or sulfuric acid are used to reduce soil pH and increase the availability of macro and micronutrients for optimum crop yield. However, how these inputs impact soil greenhouse gas emissions is unknown. This study aimed to measure the amount of greenhouse gas emissions and pH after the application of various doses of elemental sulfur (ES) and sulfuric acid (SA). Using static chambers, this study quantifies soil greenhouse gas emissions (CO2, N2O, and CH4) for 12 months after the application of ES (200, 400, 600, 800, and 1000 kg ha−1) and SA (20, 40, 60, 80 and 100 kg ha−1) to a calcareous soil (pH 8.1) in Zanjan, Iran. Also, in order to simulate rainfed and dryland farming which are common practices in this area, this study was conducted with and without sprinkler irrigation. Application of ES slowly decreased soil pH (more than half a unit) over the year whereas application of SA temporarily reduced the pH (less than a half unit) for a few weeks. CO2 and N2O emissions and CH4 uptake were maximum during summer and lowest in winter. Cumulative CO2 fluxes ranged from 1859.2 kg−1 CO2-C ha−1 year−1 in the control treatment to 2269.6 kg CO2-C ha−1 year−1 in the 1000 kg ha−1 ES treatment. Cumulative fluxes for N2O-N were 2.5 and 3.7 kg N2O-N ha−1 year−1 and cumulative CH4 uptakes were 0.2 and 2.3 kg CH4-C ha−1 year−1 in the same treatments. Irrigation significantly increased CO2 and N2O emissions and, depending on the amount of ES applied, decreased or increased CH4 uptake. SA application had a negligible effect on GHGs emissions in this experiment and only the highest amount of SA altered GHGs emissions.

Influence of broiler litter band positioning on cotton growth and yield in a Blackland Prairie soil

AbstractSubsurface band application of broiler litter in soil is being evaluated across the United States as a potential management practice for curbing phosphorus loss and improving nutrient retention. This management practice also shows promise for increasing yields of row crop systems. Determining the optimum plant distance from the subsurface banded broiler litter (BL) could be useful to optimize crop yields. Thus, a cotton (Gossypium hirsutum L.) experiment was established to investigate the distance of a subsurface BL band from the planted row on cotton growth and yield. Treatments consisted of subsurface banding BL at 0, 10, 20, 30 cm from the crop row plus a non‐fertilized check, broadcast BL, and banding of urea‐ammonium nitrate (UAN) at 20 cm to the side of rows as controls. Subsurface band placement of BL and UAN occurred just prior to sowing at a depth of 10 cm. Placing BL in subsurface bands tended to increase cotton yield compared to surface broadcasting the litter. When comparing BL band positions, cotton lint yield was generally greatest when BL was placed in subsurface bands 20 cm or less from the planted row. Minimal differences in cotton fiber quality were observed among treatments. Results suggest the reduced distance between the cotton row and a subsurface BL band can increase cotton growth and yield.

Agrivoltaic, a Synergistic Co-Location of Agricultural and Energy Production in Perpetual Mutation: A Comprehensive Review

Agrivoltaic systems, which consist of the combination of energy production by means of photovoltaic systems and agricultural production in the same area, have emerged as a promising solution to the constraints related to the reduction in cultivated areas due to solar panels used in agricultural production systems. They also enable optimization of land use and reduction in conflicts over land access, in order to meet the increasing demand for agricultural products and energy resulting from rapid population growth. However, the selected installation configurations, such as elevation, spacing, tilt, and choice of panel technology used, can have a negative impact on agricultural and/or energy production. Thus, this paper addresses the need for a review that provides a clear explanation of agrivoltaics, including the factors that impact agricultural and energy production in agrivoltaic systems, types of panel configurations and technologies to optimize these systems, and a synthesis of modelling studies which have already been conducted in this area. Several studies have been carried out in this field to find the appropriate mounting height and spacing of the solar panels that optimize crop yields, as this later can be reduced by the shade created with the solar panels on the plants. It was reported that yields have been reduced by 62% to 3% for more than 80% of the tested crops. To this end, an optimization model can be developed to determine the optimal elevation, spacing, and tilt angle of the solar panels. This model would take into account factors that influence crop growth and yield, as well as factors that affect the performance of the photovoltaic system, with the goal of maximizing both crop yield and energy production.

Impact of silicate and lime application on soil fertility and temporal changes in soil properties and carbon stocks in a temperate ecosystem

Most agricultural soils are unproductive due to soil acidity which limits crop growth and yield. To ameliorate soil acidity constraints and enhance the ecosystem services the soil renders to achieve optimum crop yields, lime, and silicate are mostly used. However, there are few studies reporting the impacts of the combined application of silicate and lime on soil properties, soil fertility and carbon stocks and stratification in long-term experiments. This study evaluated the impacts of the combined application of silicate and lime on soil fertility indicators (pH, soil organic matter (SOM), available phosphorus, exchangeable potassium, magnesium, and calcium, and available SiO2), carbon stratification and stocks in comparison to sole lime and sole silicate applied to a Fluvaquentic Eutrudepts over a 67-year period. Each treatment’s rate of application was calculated to raise the soil pH to 6.5. Incorporation of the treatments increased the soil pH by 1.30, 1.22, and 1.35 folds in the sole silicate, sole lime, and combined silicate and lime-treated soils, respectively, relative to the baseline soil pH (5.5). The combined application of silicate and lime resulted in significant decreases in C stratification and C stocks. The significant reduction in the C stocks in the silicate and lime-treated soils implies that its long-term application could potentially reduce carbon sequestration and increase the carbon footprint of rice cultivation. This information is crucial to develop sustainable soil management interventions to curtail the environmental footprint in rice paddy ecosystems. Comparatively, the combined silicate and lime treatment caused an increase in the relative change of soil fertility by 65.7% and the average annual growth rate in the soil fertility improvement by 0.0115, as compared to the untreated soil. Among the soil variables, soil pH, exchangeable calcium, and available silicate contributed most to the variation the soil fertility. The obtained results could serve as a guide in revising the lime and silicate fertilization programs instituted by the Korean Government and reviewing national soil fertility management systems in temperate paddy ecosystems.

Relationship between Phosphorus and Nitrogen Concentrations of Flax

Tools quantifying phosphorus (P) status in plants help to achieve efficient management and to optimize crop yield. The objectives of this study were to establish the relationship between P and nitrogen (N) concentrations of flax (Linum usitatissimum L.) during the growth season to determine the critical P concentration for diagnosing P deficiency. Field experiments were arranged as split plots based on a randomized complete block design. Phosphorus levels (0, 40, 80, 120, and 160 kgP2O5 ha−1) were assigned to the main plots, and cultivars (Dingya 22, Lunxuan 2, Longyaza 1, Zhangya 2, and Longya 14) were allocated to the subplots. Shoot biomass (SB) and P and N concentrations were determined at 47, 65, 74, 98, and 115 days after emergence. Shoot biomass increased, while P and N concentrations and the N:P ratio declined with time in each year. The P concentration in respect of N concentration was described using a liner relationship (P = 0.05, N + 1.68, R2 = 0.76, p < 0.01) under non-limiting P conditions, in which the concentrations are expressed in g kg−1 dry matter (DM). The N:P ratio was fitted to a second-order polynomial equation (N:P = 11.56 × SB−0.1, R2 = 0.71, p = 0.03), based on the SB of flax. This research first developed a predictive model for critical P concentration in flax, as a function of N concentration in shoots of flax. The critical P concentration can be used as a promising alternative tool to quantify the degree of P deficiency of flax during the current growing season.

VALORIZING DEGRADED LANDS USING INNOVATIVE BIOFERTILISERSFOR TOMATO CROPPING: RESPONSE TO BOKASHI, EFFICIENT MICROORGANISMS AND COMPOST IN THE SUDANESE ZONE OF BURKINA FASO (BOBO-DIOULASSO)

In order to improvefood security and sustainable land management at relatively low cost, this study evaluates the effect of biofertilizers on soil chemical properties and on tomato yield in 2020 and 2022 in Bobo-Dioulasso (Burkina Faso). A Fisher randomized design compares six treatments: T1: compost at 30 kg ha-1, T2: Bokashi at 30 kg ha-1, T3: Effective Microorganisms at 500 l ha-1, T4: T1 + T3, T5: T2+T3, T6: mineral fertilizer at 300 kg ha-1 of compound fertilizer NPK (14-23-14) + 200 kg ha-1 of urea 46% N. Results show that compost and Bokashi have the potential to improve the availability of phosphorus and exchangeable bases in soil compared to mineral fertilizer. They enable the stabilization of pH value and nitrogen content, which decrease if only mineral fertilizer is applied. Bokashi increases tomato yield by 23-58% compared to mineral fertilizer. Effective microorganisms alone are less efficient than mineral fertilizer. Combining Bokashi, whether enriched or not with effectivemicroorganisms and a minimal amount of mineral fertilizer, could help optimize crop yields in the transitional phase of soil fertility recovery. This study suggests that biofertilizers can be used to improve food production while stabilizing soil quality.

Crop Yield Prediction Using Machine Learning Models: Case of Irish Potato and Maize

Although agriculture remains the dominant economic activity in many countries around the world, in recent years this sector has continued to be negatively impacted by climate change leading to food insecurities. This is so because extreme weather conditions induced by climate change are detrimental to most crops and affect the expected quantity of agricultural production. Although there is no way to fully mitigate these natural phenomena, it could be much better if there is information known earlier about the future so that farmers can plan accordingly. Early information sharing about expected crop production may support food insecurity risk reduction. In this regard, this work employs data mining techniques to predict future crop (i.e., Irish potatoes and Maize) harvests using weather and yields historical data for Musanze, a district in Rwanda. The study applies machine learning techniques to predict crop harvests based on weather data and communicate the information about production trends. Weather data and crop yields for Irish potatoes and maize were gathered from various sources. The collected data were analyzed through Random Forest, Polynomial Regression, and Support Vector Regressor. Rainfall and temperature were used as predictors. The models were trained and tested. The results indicate that Random Forest is the best model with root mean square error of 510.8 and 129.9 for potato and maize, respectively, whereas R2 was 0.875 and 0.817 for the same crops datasets. The optimum weather conditions for the optimal crop yield were identified for each crop. The results suggests that Random Forest is recommended model for early crop yield prediction. The findings of this study will go a long way to enhance reliance on data for agriculture and climate change related decisions, especially in low-to-middle income countries such as Rwanda.

Dealing with Unbalanced Data in Leaf Disease Detection: A Comparative Study of Hierarchical Classification, Clustering-based Undersampling and Reweighting-based Approaches

Precision agriculture plays a crucial role in optimizing crop yield, reducing environmental impact, and ensuring sustainable agricultural practices. Early detection and accurate diagnosis of leaf diseases are essential for preventing significant losses in crop production and maintaining food security. However, the inherent challenge of class imbalance in leaf disease datasets poses a significant obstacle for machine learning algorithms. In this paper, we explore and compare different techniques for handling class imbalance in leaf disease detection to improve the accuracy and reliability of machine learning models in the context of precision agriculture. We investigated the performance of different methods for leaf disease detection using the challenging New Plant Diseases Dataset (NPDD), which consists of image-based plant leaves. Our experiments reveal promising results, particularly with the hierarchical approach, achieving an accuracy of 97.17%. The outcomes of our study contribute to the growing body of knowledge in precision agriculture by providing a comprehensive analysis of techniques for handling class imbalance in leaf disease detection. Furthermore, our findings serve as a valuable resource for researchers and practitioners in the field, offering guidance on selecting and implementing the most effective approaches to tackle class imbalance challenges and improving the overall performance and reliability of machine learning models in the domain of precision agriculture.