Yield Monitor Research Articles

Microbial Dynamics and Quality Monitoring in Biopharmaceutical Production

AbstractProkaryotic cells are pivotal in meeting the global demand for biopharmaceuticals. However, challenges such as the absence of advanced technology for real‐time monitoring, standardized testing methodologies, and quality risk assessment of microbial activity have led to increased production costs, delays, and shortages of biopharmaceutical products. A thorough understanding of how biomolecule production interacts with microbial population structure and function is vital for improving continuous manufacturing and process automation. In this review, we discuss the current microbiological techniques that meet good manufacturing practice requirements in industrial settings, explore the advantages of monitoring and measuring biomass growth efficiency and turnover rates beyond regulatory criteria for product release, and provide a critical assessment of the current state of knowledge on bioassays and engineering tools for biomolecule yield measurement and monitoring. Furthermore, we identify areas for future development, potential applications, and the need for interdisciplinary innovation to drive future research, including advancing bioassays for biopharmaceutical wastewater risk.

Easy yield mapping for precision agriculture

ABSTRACT Within precision agriculture, yield mapping is important in the evaluation of crop management and delineation of management zones. It can also be used to assess within-field yield potential, in order to guide different precision agriculture practices. However, some farmers do not have a yield monitoring system, and some who do may obtain incomplete or erroneous yield data. This study examined the accuracy with which winter wheat (Triticum aestivum L.) yield could be mapped in 18 fields in southern Sweden using a simple empirical relationship between Sentinel-2 (ESA, Paris, France) data, vegetation index (VI) maps and combined harvester data collected in nearby fields. The results showed that a decrease in map resolution to 40 m reduced the error in the yield maps obtained. Normalised difference water index (NDWI) was the most efficient VI, while a combination of satellite data from earlier and later plant development (booting and milk development stages) performed slightly better than data for other development stages and combinations. The best-performing model at a within-field scale (40-m resolution) had an average mean absolute error (MAE) of 0.40 tonnes ha−1 in a leave-one-field-out cross validation. When the prediction model at field-means scale was applied on 69 farms in a 1055 km2 area, MAE was 0.75 tonnes ha−1 when comparing predictions with mean yields reported by farmers in a phone survey. Therefore, if adequate combined harvester and/or mean yield data are available, a modelling framework that translates satellite imagery into yield maps on-the-fly could be made available for different stakeholders via decision support systems for precision agriculture.

Investigating the Role of Cover-Crop Spectra for Vineyard Monitoring from Airborne and Spaceborne Remote Sensing

The monitoring of grape quality parameters within viticulture using airborne remote sensing is an increasingly important aspect of precision viticulture. Airborne remote sensing allows high volumes of spatial consistent data to be collected with improved efficiency over ground-based surveys. Spectral data can be used to understand the characteristics of vineyards, including the characteristics and health of the vines. Within viticultural remote sensing, the use of cover-crop spectra for monitoring is often overlooked due to the perceived noise it generates within imagery. However, within viticulture, the cover crop is a widely used and important management tool. This study uses multispectral data acquired by a high-resolution uncrewed aerial vehicle (UAV) and Sentinel-2 MSI to explore the benefit that cover-crop pixels could have for grape yield and quality monitoring. This study was undertaken across three growing seasons in the southeast of England, at a large commercial wine producer. The site was split into a number of vineyards, with sub-blocks for different vine varieties and rootstocks. Pre-harvest multispectral UAV imagery was collected across three vineyard parcels. UAV imagery was radiometrically corrected and stitched to create orthomosaics (red, green, and near-infrared) for each vineyard and survey date. Orthomosaics were segmented into pure cover-cropuav and pure vineuav pixels, removing the impact that mixed pixels could have upon analysis, with three vegetation indices (VIs) constructed from the segmented imagery. Sentinel-2 Level 2a bottom of atmosphere scenes were also acquired as close to UAV surveys as possible. In parallel, the yield and quality surveys were undertaken one to two weeks prior to harvest. Laboratory refractometry was performed to determine the grape total acid, total soluble solids, alpha amino acids, and berry weight. Extreme gradient boosting (XGBoost v2.1.1) was used to determine the ability of remote sensing data to predict the grape yield and quality parameters. Results suggested that pure cover-cropuav was a successful predictor of grape yield and quality parameters (range of R2 = 0.37–0.45), with model evaluation results comparable to pure vineuav and Sentinel-2 models. The analysis also showed that, whilst the structural similarity between the both UAV and Sentinel-2 data was high, the cover crop is the most influential spectral component within the Sentinel-2 data. This research presents novel evidence for the ability of cover-cropuav to predict grape yield and quality. Moreover, this finding then provides a mechanism which explains the success of the Sentinel-2 modelling of grape yield and quality. For growers and wine producers, creating grape yield and quality prediction models through moderate-resolution satellite imagery would be a significant innovation. Proving more cost-effective than UAV monitoring for large vineyards, such methodologies could also act to bring substantial cost savings to vineyard management.

Integrated Analysis of Solar-Induced Chlorophyll Fluorescence, Normalized Difference Vegetation Index, and Column-Average CO2 Concentration in South-Central Brazilian Sugarcane Regions

Remote sensing has proven to be a vital tool for monitoring and forecasting the quality and yield of crops. The utilization of innovative technologies such as Solar-Induced Fluorescence (SIF) and satellite measurements of column-averaged CO2 (xCO2) can enhance these estimations. SIF is a signal emitted by crops during photosynthesis, thus indicating photosynthetic activities. The concentration of atmospheric CO2 is a critical factor in determining the efficiency of photosynthesis. The aim of this study was to investigate the correlation between satellite-derived Solar-Induced Chlorophyll Fluorescence (SIF), column-averaged CO2 (xCO2), and Normalized Difference Vegetation Index (NDVI) and their association with sugarcane yield and sugar content in the field. This study was carried out in south-central Brazil. We used four localities to represent the region: Pradópolis, Araraquara, Iracemápolis, and Quirinópolis. Data were collected from orbital systems during the period spanning from 2015 to 2016. Concurrently, monthly data regarding tons of sugarcane per hectare (TCH) and total recoverable sugars (TRS) were gathered from 24 harvest locations within the studied plots. It was observed that TRS decreased when SIF values ranged between 0.4 W m−2 sr−1 μm−1 and 0.8 W m−2 sr−1 μm−1, particularly in conjunction with NDVI values below 0.5. TRS values peaked at 15 kg t−1 with low NDVI and xCO2 values, alongside SIF values lower than 0.4 W m−2 sr−1 μm−1 and greater than 1 W m−2 sr−1 μm−1. These findings underscore the potential of integrating SIF, xCO2, and NDVI measurements in the monitoring and forecasting of yield and sugar content in sugarcane crops.

Within‐field variation of crop yield loss from cover crops

AbstractThe amount of high‐resolution agricultural data has increased rapidly in the current decade. Integration of satellite multispectral imagery, combine harvester yield monitoring data, and soil moisture mapping allows managing for within‐field variation and better interpreting on‐farm experimentation. In this study, we investigated the effect of cover crops on yield in Finland by integrating Sentinel‐2 satellite imagery (normalized difference vegetation index), topographic soil moisture indexes, and high‐resolution yield data. The experiment was run by three farmers over 4 years and serves as an example for low‐cost on‐farm experimentation. Our results confirmed earlier findings that undersown cover crops result in approximately 5% yield loss. We also found that the effect is highly variable across farms and within fields. The highest yield losses were found in areas of the field, which were wetter in the spring seeding time. The competition between crop and cover crop could be observed in the vegetation maps for autumn and early summer. Combining NDVI and soil moisture maps allows delineating field zones, which require extra management to reduce the risk of yield loss from cover crop resource competition. Evaluating the overall effect of cover crops on yield would require replication on more farms. The within‐field variation results and workflow investigated in this study can guide placement of sampling areas within those fields.

Understanding the limitations of grain yield monitor technology to inform on‐farm research

AbstractYield monitoring technology (YM) is a valuable tool to evaluate crop performance in on‐farm research (OFR). However, limited information exists on utilizing this technology to accurately inform OFR. The objectives of this study were to evaluate the ability of grain yield monitor mass flow sensors to detect changes in corn (Zea mays L.) yield for different plot lengths, provide a recommended minimum plot length to utilize YM in OFR, and determine if differences in estimating yield existed between YMs. Six treatment lengths that varied in distance of intentional yield differences (7.6, 15.2, 30.5, 61.0, 121.9, and 243.8 m) were created by alternating high‐yield (202 kg N/ha application) and low‐yield (0 kg N/ha application) plots. A total of four grain YMs with impact‐style mass flow sensors were used within two commercially available combines. Yield comparisons were made between the plot combine and YMs to evaluate the accuracy of each technology for detecting the magnitude of yield change across lengths using analysis of variance and exponential regression curves. Results indicated that the mass flow sensors were not sensitive enough to detect quickly changing flow rates for alternating yield changes in small plot lengths. Minimum plot lengths ranged from 43 to 107 m depending on YM. Significant differences were observed between grain YMs from different manufacturers. Future work could evaluate the influence additional crops or smaller yield differences have on the optimum OFR plot length.

Correlation between perennial grass productivity and landscape and climatic conditions

The yield monitoring (1998–2023) of cloverothymothy grass stands of 1 year of use within the moraine hill was carried out in order to find patterns in the influence of weather conditions on it. The grass stands were operated in the conditions of the Tver region without fertilizers in a single-cut mode on a field divided into 120 plots. Using regression analysis, we determined the influence of temporal variability of average monthly values: average daily temperatures, their amplitude, amount of precipitation and hydrothermal coefficient on the hay yield of perennial grasses. It was revealed that in total these parameters determine about 43% of the variability in grass productivity, but fluctuations in temperature amplitudes are responsible for 32% of the temporal variability of the yield. The yield of herbs is affected by the variability of growing conditions not only in time, but also in space. The negative impact on the yield of air temperature changes is observed in all parts of the landscape, except for the flat top, where productivity responds positively to the growth of the hydrothermal coefficient and negatively to the increase in air temperatures in the pre-harvest period. The following have a negative impact on product yield: temperature changes in late summer and early autumn, especially on southern slopes, which can make it difficult for plants to overwinter; thaws in March, causing the formation of an ice crust on the soil surface and damaging the tillering nodes of plants; hot days in the pre-harvest period, accelerating the ripening of grasses and reducing the intensity of biomass accumulation. February thaws, promoting the accumulation of moisture in the soil, lead to an increase in grass yield. Measures that reduce the negative impact of temperature changes on the grass harvest include: autumn mowing of young grass, snow retention in meadows, and sprinkling of grass on the hottest days of the pre-harvest period.

Research of real-time corn yield monitoring system with DNN-based prediction model.

The real-time monitoring of corn yield by a combine harvester is a critical data source for constructing the yield histogram, which significantly benefits precision management and decision-making in modern precision agriculture. While widely used, the current photoelectric sensor-based yield monitoring method has limitations. It detects the corn height on each scraper and calculates the yield through a geometric formula. However, it neglects the noticeable difference in the corn stacking patterns affected by factors such as feeding volume, terrain, and driving speed. This oversight often results in low accuracy and poor stability in the prediction of corn yield, highlighting the need for a more advanced approach. To resolve this, we employ EDEM discrete element simulation to demonstrate the large difference of corn stacking patterns on the scraper of the elevator corresponding to feeding volume. Then, we develop a real-time monitoring system on our self-developed double elevator testing rig for carrying out a composite dataset for training three machine learning algorithm-based models, namely Deep Neural Networks (DNN), Gradient Boosting Machine (GBM), and Random Forest (RF). Importantly, these models have undergone rigorous validation under various feeding volumes, ensuring their robustness and reliability. The auxiliary elevator speed is meticulously set at 150r/min, 225r/min, and 450r/min, providing a comprehensive performance assessment. The results denote that the DNN model performs best and is stable, with a coefficient of determination (R2) of 0.998, root mean square error (RMSE) of 0.526, and mean absolute error (MAE) of 0.425. The paper also performs field experiments to test the proposed three prediction models and the system. The results also denote the DNN-based prediction model's best performance for the lowest relative error of 2.29% and the highest average accuracy of 97.85%. Consequently, the proposed real-time corn yield monitoring system achieves high accuracy and reliability for the combine harvester applications.

Data Analytics in Agriculture: Enhancing Decision-Making for Crop Yield Optimization and Sustainable Practices

Collaboration across the agriculture supply chain is essential to address the high-yield demand and sustainable practices amid global overpopulation. Limited resources, such as soil and water, are compromised by excessive chemical agents and nutrient use. The Internet of Things (IoT) and smart farming offer solutions by optimizing agent applications, data analysis, and farm monitoring. Evidence from numerous studies indicates that collaboration in the supply chain, including farmers, can improve efficiency and productivity, reduce costs, and enhance crop quality. This paper investigates the transformation of traditional agriculture into smart farming through the integration of IoT technology and community partnerships. It presents a case study focused on educating farm owners about advanced technologies to enhance decision-making, improve crop yields, and promote sustainability. Additionally, the paper highlights the role of data analytics in agriculture. Farmers in the southern region of Zagreb, Croatia, were trained on the use of sensors and yield monitoring. Small farms in that region face challenges in improving yields due to limited capacity and lack of entrepreneurial experience. The DMAIC methodology was employed to address these issues and measure relevant parameters. The paper also discusses consistent patterns between electrical conductivity (EC) measurements and potassium levels in soil. It explains the potential of estimating potassium concentrations based on EC readings, or vice versa. Leveraging EC as a proxy for potassium levels could offer a cost-effective means of assessing soil fertility and nutrient dynamics. Additionally, Principal Component Analysis (PCA) biplot analysis is presented, showing that pH values behaved independently. Understanding these dynamics enhances knowledge of soil variability and informs sustainable soil management practices.

Crop yield estimation at different growing stages using a synergy of SAR and optical remote sensing data

Crop yield forecasting is an essential component of crop production assessment, impacting people at the global scale down to the level of individual farms. Until now, yield forecasting has predominantly relied on optical data, particularly the maximum value of vegetation indexes. However, this approach only presents a short forecasting window, and it is essential to obtain yield estimates as early as possible in the growing season and then further improve forecasting even after the vegetation index has reached its peak. So far, optical satellite data at high-temporal resolution (1–3 days) has been actively used for real time crop yield monitoring, whereas fewer operational models make a use of synthetic aperture radar (SAR). In this study, we explore whether SAR data can capture distinct aspects of crop dynamics, providing new insights for yield estimation depending on the crop's phenological stage. We assess the efficiency of dual- (Sentinel-1) and quad-polarimetric (UAVSAR, RADARSAT-2) data to explain inter-field crop yield variability for corn, soybean, and rice over a test area in Arkansas, US (258 fields, 2019). We used optical imagery acquired by Planet/Dove-Classic, Sentinel-2, and Landsat 8, to establish a baseline performance of satellite-based indicators to explain yield variability and assess dual- and quad-polarimetric SAR data for crop yield assessment. In terms of polarimetric indexes, the results showed that in general the results for rice were mostly stable and better than the other crops (R2adj ∼ 0.4 on average). The best results were obtained for the Sentinel-1 VHasc with R2adj = 0.47 and RADARSAT-2 phase difference with R2adj = 0.45. The results for corn performed the least with an R2adj <0.35 for all the indexes. The results for soybeans were more variable and were highly correlated with certain indicators such as RADARSAT-2 HV, RADARSAT-2 Volume, and RADARSAT-2 Pauli HV with R2adj>0.4. We also investigated the day of year (DOY) with the maximum correlation between optical and SAR-derived features and the final yields for corn, soybean, and rice. The maximum correlation for optical features occurs over a short time between DOY 155 (June 4) and 185 (July 5) for corn and rice, and DOY 190 (July 9) and DOY 211 (July 30) for soybean, with these results being consistent across various optical-based sensors. On the contrary, the maximum correlation for SAR-derived features varied significantly and was between DOY 120 (April 30) to DOY 225 (August 13). A study of the time series parameters cross-correlation showed that the optical parameters were highly correlated, but the SAR parameters showed strong temporal decorrelation. We conducted a comparison between C-band and L-band to assess their sensitivity at each stage of growth. In this experiment, we determined that for low vegetation, the C band will be more useful at the beginning of the growth cycle, while the L band provides more information in later stages of growth. Using a random forest regression model combining SAR parameters with common difference vegetation index (DVI), we improved the error by 50% in comparison to the error using the (DVI) for corn, soybean, and rice.

Garlic yield monitoring using vegetation indices and texture features derived from UAV multispectral imagery

Remote sensing and machine learning are widely used to estimate crop yield. The use of these technologies for yield estimation of bulbous vegetables is challenging because the yield is underground and can't be directly monitored by remote sensing images. Among the bulbous vegetables, garlic (Allium sativum L.) is one of the most widely cultivated in the world. The aim of this study was to develop an accurate and transferable machine learning model to monitor and to estimate garlic yield using unmanned aerial vehicle (UAV) multispectral images. Data were collected over three growing seasons (2021, 2022, and 2023) at four different garlic phenological phases (202, 405, 407, and 409 of BBCH). The random forest (RF) algorithm was used to estimate the garlic yield by comparing two different training feature sets: the vegetation indices (VIs) and the VIs with the addition of the texture features extracted from the UAV images. The most important VIs were selected using the recursive feature elimination algorithm. Two estimation methods were compared: a direct bulb estimation and an indirect bulb estimation using the aboveground biomass as a proxy. To evaluate the transferability of the RF models, two cross-validation strategies were compared: a nested leave-one-fold-out cross-validation (LOFOCV) and a leave-one-year-out cross-validation (LOYOCV). The best performance was achieved by the direct bulb estimation using the LOFOCV strategy. Regarding the transferability of the RF models between years (i.e. LOYOCV), the indirect estimation method showed a higher transferability than the direct estimation method. Finally, the addition of texture features improved the accuracy of the RF models, but in general, their contribution was poor. This study demonstrated that the yield of bulbous vegetables can be accurately estimated by remote sensing, and that UAVs are a suitable tool to provide rapid and reliable support for garlic yield monitoring.

Milk Quality and Economic Sustainability in Dairy Farming: A Systematic Review of Performance Indicators

The dairy industry plays a vital role in the global food system, providing a wide range of dairy products that are consumed by millions of people worldwide. Dairy farming provides a daily source of income, creating employment opportunities not only on farms, but also in transportation, milk processing, and the agricultural supply and services sectors. The increasingly pressing challenges and the high competition in the dairy industry, particularly in saturated markets, emphasize the importance for farms to undertake a comprehensive economic sustainability analysis that extends beyond mere yield monitoring. Empirical studies have found a weak adoption of robust performance measurement and control systems in dairy farms. Given the intricate macroeconomic landscape in developed nations and the imperative to address the multifaceted challenges of the industry, this study employs a systematic literature review (SLR) to evaluate whether academic research offers adequate guidance on economic performance indicators. The study finds out that the current repertoire of indicators, while relevant and partially related to quality attributes, fails to encapsulate the intricate interplay of variables and the nature of economic sustainability, highlighting the need to adopt additional indicators into the dimensions of operational efficiency and effectiveness, strategic investments, and financial strength.

Early-Season Crop Mapping by PRISMA Images Using Machine/Deep Learning Approaches: Italy and Iran Test Cases

Despite its high importance for crop yield prediction and monitoring, early-season crop mapping is severely hampered by the absence of timely ground truth. To cope with this issue, this study aims at evaluating the capability of PRISMA hyperspectral satellite images compared with Sentinel-2 multispectral imagery to produce early- and in-season crop maps using consolidated machine and deep learning algorithms. Results show that the accuracy of crop type classification using Sentinel-2 images is meaningfully poor compared with PRISMA (14% in overall accuracy (OA)). The 1D-CNN algorithm, with 89%, 91%, and 92% OA for winter, summer, and perennial cultivations, respectively, shows for the PRISMA images the highest accuracy in the in-season crop mapping and the fastest algorithm that achieves acceptable accuracy (OA 80%) for the winter, summer, and perennial cultivations early-season mapping using PRISMA images. Moreover, the 1D-CNN algorithm shows a limited reduction (6%) in performance, appearing to be the best algorithm for crop mapping within operational use in cross-farm applications. Machine/deep learning classification algorithms applied on the test fields cross-scene demonstrate that PRISMA hyperspectral time series images can provide good results for early- and in-season crop mapping.

Quantifying the carbon sequestration potential of different soil management practices aimed at increasing organic content in soil and reducing the usage of chemical inputs

&lt;p&gt;The global imperative to address climate change and promote sustainable agriculture has underscored the critical role of soil management practices in enhancing carbon sequestration and reducing greenhouse gas emissions. This research focuses on quantifying the carbon sequestration potential of diverse soil management techniques aimed at increasing organic content in soil while minimizing the use of chemical inputs. It integrates a multidisciplinary approach, conducting field experiments across diverse agroecological regions with different soil types and cropping systems. Key practices under investigation include cover cropping, crop rotations, conservation tillage, compost application, organic amendments, integrated pest management (IPM), and precision agriculture. The study assesses their impact on soil organic carbon levels, greenhouse gas emissions, soil health indicators, and crop productivity through comprehensive data collection and analysis techniques. Statistical analyses and modeling are employed to quantify carbon sequestration rates, evaluate treatment effects, and assess environmental and agronomic benefits. These practices are implemented in controlled trials to assess their impact on soil organic carbon (SOC) levels, greenhouse gas emissions (CO2, CH4, N2O), soil health indicators (microbial biomass, nutrient cycling, soil structure), and crop productivity. Data collection and analysis techniques involve comprehensive soil sampling, greenhouse gas flux measurements, soil health assessments, and crop yield monitoring over multiple growing seasons. Statistical analyses and modeling approaches are employed to quantify the carbon sequestration rates, assess treatment effects on soil health and greenhouse gas emissions, and evaluate the overall environmental and agronomic benefits of the soil management practices. The study aims to contribute valuable insights into evidence-based strategies for promoting sustainable soil management practices that enhance carbon sequestration while maintaining or improving agricultural productivity. The findings will have implications for informing agricultural policies, guiding farm management decisions, and advancing research on climate-smart agriculture. By quantifying the carbon sequestration potential of different soil management practices, this research contributes to the broader goal of achieving climate resilience, environmental sustainability, and food security in agricultural systems.&lt;/p&gt;

Development of a Cross-Platform Mobile Application for Fruit Yield Estimation

The Fruit Harvest Helper, a mobile application developed by Northwest Nazarene University’s (NNU) Robotics Vision Lab, aims to assist farmers in estimating fruit yield for apple orchards. Currently, farmers manually estimate the fruit yield for an orchard, which is a laborious task. The Fruit Harvest Helper seeks to simplify their process by detecting apples on images of apple trees. Once the number of apples is detected, a correlation can then be applied to this value to obtain a usable yield estimate for an apple tree. While prior research efforts at NNU concentrated on developing an iOS app for blossom detection, this current research aims to adapt that smart farming application for apple detection across multiple platforms, iOS and Android. Borrowing ideas from the former iOS app, the new application was designed with an intuitive user interface that is easy for farmers to use, allowing for quick image selection and processing. Unlike before, the adapted app uses a color ratio-based image-segmentation algorithm written in C++ to detect apples. This algorithm detects apples within apple tree images that farmers select for processing by using OpenCV functions and C++ code. The results of testing the algorithm on a dataset of images indicate an 8.52% Mean Absolute Percentage Error (MAPE) and a Pearson correlation coefficient of 0.6 between detected and actual apples on the trees. These findings were obtained by evaluating the images from both the east and west sides of the trees, which was the best method to reduce the error of this algorithm. The algorithm’s processing time was tested for Android and iOS, yielding an average performance of 1.16 s on Android and 0.14 s on iOS. Although the Fruit Harvest Helper shows promise, there are many opportunities for improvement. These opportunities include exploring alternative machine-learning approaches for apple detection, conducting real-world testing without any human assistance, and expanding the app to detect various types of fruit. The Fruit Harvest Helper mobile application is among the many mobile applications contributing to precision agriculture. The app is nearing readiness for farmers to use for the purpose of yield monitoring and farm management within Pink Lady apple orchards.

Predicting Winter Wheat Yield with Dual-Year Spectral Fusion, Bayesian Wisdom, and Cross-Environmental Validation

Winter wheat is an important grain that plays a crucial role in agricultural production and ensuring food security. Its yield directly impacts the stability and security of the global food supply. The accurate monitoring of grain yield is imperative for precise agricultural management. This study aimed to enhance winter wheat yield predictions with UAV remote sensing and investigate its predictive capability across diverse environments. In this study, RGB and multispectral (MS) data were collected on 6 May 2020 and 10 May 2022 during the grain filling stage of winter wheat. Using the Pearson correlation coefficient method, we identified 34 MS features strongly correlated with yield. Additionally, we identified 24 texture features constructed from three bands of RGB images and a plant height feature, making a total of 59 features. We used seven machine learning algorithms (Cubist, Gaussian process (GP), Gradient Boosting Machine (GBM), Generalized Linear Model (GLM), K-Nearest Neighbors algorithm (KNN), Support Vector Machine (SVM), Random Forest (RF)) and applied recursive feature elimination (RFE) to nine feature types. These included single-sensor features, fused sensor features, single-year data, and fused year data. This process yielded diverse feature combinations, leading to the creation of seven distinct yield prediction models. These individual machine learning models were then amalgamated to formulate a Bayesian Model Averaging (BMA) model. The findings revealed that the Cubist model, based on the 2020 and 2022 dataset, achieved the highest R2 at 0.715. Notably, models incorporating both RGB and MS features outperformed those relying solely on either RGB or MS features. The BMA model surpassed individual machine learning models, exhibiting the highest accuracy (R2 = 0.725, RMSE = 0.814 t·ha−1, MSE = 0.663 t·ha−1). Additionally, models were developed using one year’s data for training and another year’s data for validation. Cubist and GLM stood out among the seven individual models, delivering strong predictive performance. The BMA model, combining these models, achieved the highest R2 of 0.673. This highlights the BMA model’s ability to generalize for multi-year data prediction.

Estimation of potato yield using a semi-mechanistic model developed by proximal remote sensing and environmental variables

Timely monitoring of potato yield status is crucial for guiding field management and ensuring the sustainability of food trade. In recent years, non-destructive remote sensing techniques have emerged as one of the most promising methods for crop yield monitoring. However, most existing potato yield estimation models have primarily been tested at specific growth stages within a single ecosystem, highlighting the urgent need for a model that can be applied across different ecological environments. In this study, we developed a semi-physical model based on hierarchical linear modeling (HLM) to automatically correct yield estimation based on remotely sensed vegetation indices using environmentally relevant variables such as net solar radiation at the surface (ssr), air temperature at 2 m above the surface (t2m), and soil water content in the root zone (swvl). The accuracy and transferability of the model were further evaluated by comparing it with aboveground destructive sampling methods, conventional empirical models, and machine learning approaches. The results demonstrated that site-specific relationships exist between aboveground agronomic traits parameters like biomass and leaf area index (LAI) with respect to yield estimation. Conventional linear statistical and machine learning methods faced challenges in transferring their constructed yield estimation models across regions and years. However, the HLM approach exhibited excellent generalization ability across all trial samples. In the middle and later stages of potato growth, the standardized LAI determining index proved to be the most effective vegetation for predicting yield, while ssr, sktmax, and shallow swvl were identified as key environmental variables affecting yield. By integrating these variables using HLM modeling techniques, we achieved optimal generalization performance (R2 = 0.57, RMSE = 7.65 t/ha, NRMSE = 25.02 % during tuber growth stage; R2 = 0.60, RMSE = 7.37 t/ha, NRMSE = 24.13 % during starch accumulation stage). This study underscores the importance of considering environmental factors when constructing a reliable model for estimating potato yield at different spatial and temporal scales using remote sensing technology.

Application of Irrigation Management and Water-Lifting Technologies to Enhance Fodder Productivity in Smallholder Farming Communities: A Case Study in Robit Bata, Ethiopia

Small-scale cultivation of irrigated fodder is emerging as a vital production system in mixed farming communities. Efficient water management plays a key role in enhancing forage production, especially in the face of changing climate. A field-scale experimental study was conducted in Robit Bata kebele, Ethiopia, with the following objectives: (1) to examine the effects of conventional farmers’ irrigation scheduling versus climate-based irrigation scheduling; and (2) to assess the influence of water-lifting technologies (manual pulley and solar Majipump) on dry matter yield (DMY), water productivity (WP), irrigation labor productivity (ILP), and water productivity in terms of crude protein and metabolizable energy (WP.CP and WP.ME) of Napier grass. The experiment used 10 farmers’ plots each with a size of 100 m2. Half of the plots were treated using farmers’ scheduling while the other half were treated using climate-based irrigation scheduling. Monitoring of irrigation water use and crop yield took place over two irrigation seasons from November 2020 to June 2021. Results showed there was an interaction effect of irrigation management (p = 0.019) and water-lifting technologies (p = 0.016) with season on DMY. The highest DMY occurred in the first irrigation season with climate-based scheduling and solar Majipump use. The interaction effect of irrigation management and season affected WP (p = 0.047). Climate-based scheduling had a higher WP in the first season, while farmers’ scheduling had a higher WP during the second season. On average, the solar Majipump outperformed the pulley, achieving 5 kg m−3 WP compared to the pulley’s 4 kg m−3 (p = 0.018). Emphasizing the seasonal impact, it is recommended to promote full irrigation (climate-based) in the first season for maximum yield and WP. Conversely, in the second season, advocating only deficit irrigation is advised due to water scarcity and sustainability concerns. Statistical parity in DMY and lower WP with full irrigation in the second season supports this recommendation, addressing the challenge of optimizing water use in the context of a changing climate and ensuring sustainable smallholder agriculture practices. Therefore, implementing appropriate irrigation management alongside efficient water-lifting technologies holds the potential to enhance fodder productivity and bolster smallholder farmers’ livelihoods. Future research should explore the comparative benefits of irrigated fodder versus other crops and the overall advantages of investing in irrigated fodder over vegetables.

AI ENABLED WATER CONSERVATION FOR IRRIGATION USING IOT

This project introduces a smart irrigation system that utilizes Internet of Things (IoT) technology and machine learning algorithms to enhance water management in agriculture. The system employs a series of IoT sensors distributed across the field to consistently monitor key environmental factors such as soil moisture levels, temperature, humidity, and others. The collected data is analysed using machine learning Cat Boosting algorithm. This algorithm analyze the data to determine the optimal irrigation schedule based on crop water requirements, soil conditions, weather forecasts, and historical data. The system controls irrigation equipment such as pumps, valves, and sprinklers to deliver precise amounts of water to crops at the right time. Continuous feedback from the system allows for refinement of irrigation schedules, leading to improved water conservation, increased crop yield, and cost savings for farmers. This project discusses the benefits of such a system, including water conservation, increased crop yield, cost savings, environmental sustainability, and remote monitoring and control capabilities. Overall, the integration of IoT and machine learning technologies offers a powerful solution for sustainable agriculture, enabling data-driven decision-making processes to optimize water usage and maximize crop productivity. Keywords— Smart irrigation system, Internet of Things(IOT)technology, Water conservation, Environmental parameters, Soil moisture monitoring, Increased crop yield, Machine learning algorithms

Optimal Timing of Carrot Crop Monitoring and Yield Assessment Using Sentinel-2 Images: A Machine-Learning Approach

Remotely sensed images provide effective sources for monitoring crop growth and the early prediction of crop productivity. To monitor carrot crop growth and yield estimation, three 27 ha center-pivot irrigated fields were studied to develop yield prediction models using crop biophysical parameters and vegetation indices (VIs) extracted from Sentinel-2A (S2) multi-temporal satellite data. A machine learning (ML)-based image classification technique, the random forest (RF) algorithm, was used for carrot crop monitoring and yield analysis. The VIs (NDVI, RDVI, GNDVI, SIPI, and GLI), extracted from S2 satellite data for the crop ages of 30, 45, 60, 75, 90, 105, and 120 days after plantation (DAP), and the chlorophyll content, SPAD (Soil Plant Analysis Development) meter readings, were incorporated as predictors for the RF algorithm. The RMSE of the five RF scenarios studied ranged from 7.8 t ha−1 (R2 ≥ 0.82 with Scenario 5) to 26.2 t ha−1 (R2 ≤ 0.46 with Scenario 1). The optimal window for monitoring the carrot crop for yield prediction with the use of S2 images could be achieved between the 60 DAP and 75 DAP with an RMSE of 8.6 t ha−1 (i.e., 12.4%) and 11.4 t ha−1 (16.2%), respectively. The developed RF algorithm can be utilized in carrot crop yield monitoring and decision-making processes for the self-sustainability of carrot production.