Subsurface soil moisture is a primary determinant for root development and nutrient transportation in the soil and affects the tractability of agricultural vehicles. A statistical forecasting model, Vector AutoRegression (VAR), and a Long Short-Term Memory network (LSTM) were developed to forecast the subsurface soil moisture at a 20 cm depth using 9 years of historical weather data and subsurface soil moisture data from Fort Wayne, Indiana, USA. A time series analysis showed that the weather data and soil moisture have a stationary seasonal tendency and demonstrated that soil moisture can be forecasted from weather data. The VAR model estimates volumetric soil moisture of one-day ahead with an R², MAE (m³m⁻³), MSE (m⁶m⁻⁶), and RMSE (m³m⁻³) of 0.698, 0.0561, 0.0046, and 0.0382 for 2021 corn cropping season, whereas the LSTM model using inputs of previous seven days yielded R², MAE (m³m⁻³), MSE (m⁶m⁻⁶), and RMSE (m³m⁻³) of 0.998, 0.00237, 0.00002, and 0.00382, respectively as tested for cropping season of 2020 and 0.973, 0.00368, 0.00003 and 0.00577 as tested for the cropping season of 2021. The LSTM model presents a viable data-driven alternative to traditional statistical models for forecasting subsurface soil moisture.

Potatoes are essential for meeting the world's dietary requirements due to their high concentration of carbohydrates, vitamins, and minerals. Potato production is plentiful worldwide, but postharvest processing losses have reduced potato quality. Potatoes can be graded manually, which is time-consuming and labor-intensive. In this study, a neural network regression model was developed to predict the volume of potatoes using 2D images, which can be used as a parameter for grading potatoes automatically. The image processing method was used to extract features like the major axis, minor axis, and roundness of 400 potato samples, and each potato's volume was thoroughly measured using the water displacement method, and a dataset was generated. These attributes were used to create the neural network regression model and predict the volume. The results revealed that the mean squared error (MSE) was 83.93, the root mean squared error (RMSE) was 9.16, and R2 was approximately 0.882. The potatoes were categorized into three groups: small, medium, and large, based on their size. The utilized model demonstrated an overall accuracy rate of 91.4%. Specifically, it achieved 90% and 85% accuracy for small-sized and medium-sized potatoes, respectively, whereas the model displayed a decrease in accuracy from 60% to 70% for large-sized potatoes. To summarize, the suggested neural network regression model provided an efficient approach to volume prediction using 2D images to improve the grading process of agricultural products.

A manually operated push type seeder was tested in laboratory testing bed near the workshop of DFPM, Bangladesh Agricultural University, Mymensingh. Seeds of different variety were sown by a single seeder changing its metering device. The seeder was calibrated in the lab to maintain the desired seed rate for maize, wheat, black gram and groundnut. In the laboratory test the effective field capacity, average distance of dropped seed and missing rate were found as 0.128 ha/hr, 22.5 cm, and 13.43%, for maize, 0.063 ha/hr, 28.5 cm, 19% for wheat, 0.053 ha/hr, 17 cm, 14.29% for black gram, 0.055 ha/hr, 17 cm and 17.86% for ground nut respectively. The field efficiency of the seeder was also quite satisfactory. Despite of comparatively high missing rate, the machine might be acceptable since it is easy to operate, simple in design and mechanism, light in weight, requires less labor and the most significant feature is using one seeder for different types of crop by adjusting the metering devices only. Modification of the seed metering devices could give better performance of the seeder.

The effective functioning of combine harvesters is crucial for the agricultural industry, especially in the harvesting of grain crops, which is vital for food security and economic stability. This study examines the replacement intervals of travelling unit spare parts in combine harvesters, employing data gathered from 87 combine harvesters across nine brands in various districts of Bangladesh. The study seeks to deliver quantitative insights into these essential components' lifespan and replacement requirements, emphasizing the monitoring of running hours and replacement intervals. The data analysis indicates considerable discrepancies in replacement intervals across various spare components and types of harvesters. The research revealed that approximately 45% of the harvesters required new sprockets, with head feed (HF) models exhibiting greater wear than full feed (FF) models. Nearly 47% of crawlers required replacement due to prolonged usage. Approximately 24% of rollers required replacement, with the majority exceeding 600 hours of usage. Conversely, 96% of carrier rollers remained in satisfactory condition without requiring replacement, indicating their durability. One-third (33%) of rear rollers needed replacement, with HF models requiring earlier substitutions than FF versions. Approximately 18% of guides were substituted, with HF models exhibiting reduced lifespans. Merely 10% of tension frames needed modifications, whereas HF models demanded modifications more frequently. HF harvesters necessitated repairs and component replacements more frequently, whereas FF harvesters exhibited greater longevity before needing maintenance. This study provides essential insights for industry stakeholders and policymakers when deciding equipment maintenance and management methods. J Bangladesh Agril Univ 23(2): 231-240, 2025