Smart agricultural technology最新文献

The objective of this study was to evaluate the levels of desethylatrazine (DEA), a hydrophilic metabolite of atrazine, and its impact on plant health. This was achieved by utilizing multispectral imagery captured by Unmanned Aerial Vehicles (UAVs) in combination with ground-measured data to assess photosynthetic pigment levels in Green Cos lettuce following atrazine application in agricultural soil. Strong correlations were found between DEA levels and chlorophyll a, chlorophyll b, and anthocyanin levels in lettuce (R² > 0.70), while the correlation with carotenoid levels was weaker (R² = 0.55). This disruption to the pigments could interfere with photosynthesis, potentially hindering the plant's growth and development, and ultimately leading to a reduction in yield. The Anthocyanin Reflectance Index (ARI) demonstrated a robust positive correlation with DEA, whereas the Normalized Difference Red Edge (NDRE), Leaf Chlorophyll Index (LCI), and Normalized Difference Vegetation Index (NDVI) displayed pronounced negative correlations. Incorporating ARI, LCI, and NDRE, with or without NDVI, provided the most accurate prediction of DEA levels, with an R² exceeding 0.96. NDRE emerged as the most efficient index for forecasting chlorophyll a and chlorophyll b levels. Modified Chlorophyll Absorption in Reflectance Index (MCARI) demonstrated the best fit for carotenoids, while ARI performed exceptionally well in describing actual measurements of anthocyanins (R² = 0.90). The best-performing VI models, developed from the selection of effective single variables, exhibited the best fit to actual pigment measurements (R² > 0.83). These findings underscore the role of UAV-derived multispectral imagery in assessing DEA levels and improving environmental monitoring, aiding in better planning for agriculture and environmental remediation to enhance ecosystem health and resilience.

To establish an indirect method for estimating and partitioning pasture evapotranspiration, it is vital to develop a direct reference method that aligns with the required temporal and spatial resolution. An evapotranspiration chamber offers an effective solution as it is easy to deploy and operates at an appropriate measurement scale. In this study, we prepared and tested a closed hemispherical chamber for on-site measurements of evaporation and/or transpiration. Advanced data monitoring and logging techniques were integrated to enhance the precision and reliability of direct in-field evapotranspiration measurements. During laboratory testing, vapor accumulation within the chamber was monitored to identify the best representative segment of the vapor accumulation curve. Results indicated that the instrument stabilizes its readings within 5 to 10 s post-deployment in laboratory settings. The subsequent 15 s produce stable readings that best represent actual vapor accumulation. The optimal fan speed, producing an air speed of 5.36 ms⁻¹ at the vicinity of the fan within the chamber, paired with a wire mesh above the vapor-producing surface, yielded the best results. The study established a calibration factor (C) of 1.02 based on the actual water loss and vapor accumulation readings from the sensors at this fan speed. Advanced data analytics were applied to derive the calibration factor and to calculate the values of evapotranspiration from the changing microclimate within the chamber. Direction towards complete automation and the limitations of the chamber in field measurement are provided. The chamber was also tested under field conditions, and the paper examines its practical application and necessary adjustments for field measurements.

This survey comprehensively examines the public irrigation decision support systems (IDSS) in Italy, offering a detailed description, analysis and evaluation of their features. The study investigates the agrometeorological networks and infrastructures that support Italian IDSS, providing a clearer understanding of the national context. The evaluation criteria include relevant factors such as soil moisture monitoring, crop water requirements (CWR) estimation models, biophysical parameters along with their spatial and temporal resolutions, irrigation planning and decision support visualization. Additionally, the assessment covers accessibility, scalability and interoperability of these systems. The survey also highlights the strengths and weaknesses of various IDSS, such as IRRIFRAME, IRRISIAS and IRTO, discussing their operational methodologies, data integration and regional coverage. The aim is to provide insights that facilitate advancements in sustainable irrigation management practices and address key challenges for future developments at both regional and national levels. This comprehensive evaluation seeks to enhance the effectiveness of IDSS in promoting sustainable water management in agriculture across Italy.

While the choice of spectrometer can vary depending on its intended use, the increased cost of high-performance spectrometers may not be justified in certain applications. Therefore, this research developed an affordable and portable device using 18-band spectral sensors incorporating a deep learning model for accurately determining the moisture content in rubber sheets. A set of 286 rubber sheets was randomly separated into two categories: 200 for model calibration and 86 for model validation. In the calibration process, the spectral data were calibrated using a one-dimensional convolutional neural network (1D-CNN) and then were compared with a recognized linear model using partial least squares regression (PLSR). The experiments revealed the exceptional performance of the 1D-CNN model in predicting the moisture content of rubber sheets, outperforming the PLSR model. The 1D-CNN model had a better prediction accuracy, with a coefficient of determination (R²) of 0.962, a root mean squared error of prediction (RMSEP) of 0.410 %, a prediction-to-deviation ratio (RPD) of 5.2, and an error range ratio (RER) of 18.0. A portable device was constructed by incorporating the 1D-CNN model into a 32-bit microcontroller, which was embedded within the measurement device. During testing of the instrument, the results indicated that its predictive performance did not differ significantly from that of the primary calibration model. Therefore, it could be concluded that the designed instrument was capable of accurately measuring the moisture content of rubber sheets and is suitable for field use due to its portability and cost-effectiveness.

Yield prediction has long been a valuable tool for farmers seeking to enhance crop production. Among the many ways to predict yield, the integration of machine learning (ML) techniques is becoming more common for refining prediction methodologies. This study highlights the current landscape of remote sensing and ML techniques employed in predicting tree crop yield while also identifying critical gaps and areas for further exploration. Studies with limited datasets for training often use simpler models such as linear regression, while studies with larger datasets use more complex models, including techniques such as deep learning, ensemble methods, and hyperparameter tuning; in these cases, the performance evaluation tends to be more sophisticated. Yield prediction using ML has demonstrated accuracy levels ranging from 50 % to 99 %. Studies using smaller datasets consistently demonstrate higher accuracy rates. While ML techniques can enhance yield prediction, their effectiveness depends on strategic data collection and a multi-factor and multi-method approach. Integration of various data sources, including weather, soil, and plant data, could enhance model resilience and applicability. Enhancing research in this field could be achieved through overcoming challenges in accurate data collection and fostering the development of open datasets. This comprehensive analysis lays the groundwork for future research endeavors aimed at refining and advancing the application of remote sensing and ML techniques in accurately predicting tree crop yield.

The cold weather-related economic losses in the aquaculture and fisheries industries are enormous and will only increase due to future climate change. Advancements in weather forecasting have increased the accuracy of predicting environmental factors like air temperature, solar radiation, and wind speed. However, the water temperature of fishponds, which affects the lives of fish, cannot be accurately predicted. As a result, fishermen are unable to implement early disaster mitigation and avoidance measures effectively. In this study, we developed an early warning system for extreme temperature events in fishponds by using a weather forecasting model in combination with local observations from a customized sensor placed in a pond. This system could provide water temperature forecasts with up to 120 h of lead time. A fishpond and multiple events were selected to assess the performance. Compared to the actual observations, the predicted water temperature difference had a root mean square error of <2 °C for up to 72 h of lead time. Furthermore, due to limited computational resources for weather forecasting models, the water temperature and depth data collected by the sensor improved the accuracy of temperature prediction specific to each pond. The results have confirmed that the integrated method can effectively predict the water temperature of farmed fishponds and assist fishermen in implementing precautionary measures in time.

Weed damage in rice fields is one of the main causes of reduced rice yields and quality. Accurate and efficient weed identification is the prerequisite for realizing intelligent and precise weeding in paddies. Recently, Vision Transformers (ViTs) have emerged with superior performance on computer vision tasks compared to the convolutional neural network (CNN)-based models. However, the lack of fully labeled weed datasets hinders the potential application of deep learning models in weed identification. To address the above issues, this study customizes a novel point-supervised instance segmentation network (PIS-Net) for weakly supervised instance segmentation of weeds in rice fields. More correctly, we first propose a novel instance segmentation point labeling scheme that utilizes randomly generated annotation points within each instance, aiming to decrease both labeling time and difficulty. Additionally, to make optimal use of point labels, this study puts forth a mask generation strategy based on the adaptive selection of pyramid levels. In this sense, the network model can flexibly choose the pyramid level expected to generate the most suitable instance mask based on the network's reliability. Finally, we establish the pseudo label refinement network (PLR-Net) to refine rough instance masks. The proposed PIS-Net utilizes 13 randomly generated annotation points for each instance, yet achieving an AP of 38.5 and an AP50 of 68.3, which is superior to the baseline mask-R-CNN with an AP of 8.2 and AP50 of 6.9, achieving 90 % fully supervised performance. This method effectively utilizes point labels, annotated with high efficiency, as a robust source of weak supervision to address challenges in weed data annotation and the low accuracy of existing weakly supervised models. Experiments show that the point annotation scheme of the PIS-Net is faster than full-object mask annotation, and the AP is also higher than the current semi-supervised weed segmentation model, enjoying high potentials in practical paddy fields.

This study investigates the impact of Chinese smallholders’ adoption of Information and Communication Technologies—the use of smartphones and computers connected to the internet—on their commercial orientation, land, and labor productivity. Commercial orientation is the share of farm output for sales in the market. We used a control function approach and a selectivity-corrected model. The study uses national survey data from rural sample households, the China Household Database, and the China Household Finance Survey and Research Center. Findings reveal that the adoption of information and communication technologies by Chinese farmers increased the commercial orientation of farming. Furthermore, adopting information and communication technologies increases land and labor productivity by about 21.3 % and 28.2 %, respectively. Farm households’ commercial orientation improved labor productivity by about 35.9 %. Heterogeneity indicates that the adoption of information and communication technologies has a more significant effect on improving productivity for young household heads and small farmers. Policymakers should establish information and communication technologies training programs, develop digital infrastructure, and promote smallholder commercial production to increase agricultural productivity.

The Qazaq Aqbas beef breed is the most important in Kazakhstan. The breed is very well adapted to the harsh conditions in Central Asia. Other more productive breeds need additional costs to ensure their survival and productivity. However, their production levels are lower than other beef breeds globally. It may be possible to improve this by selecting bulls that have greater feed efficiency. This case study reports analyses of feed intakes and weight gains by this breed on farms in Kazakhstan. Twenty-nine bulls were selected, and fed using the GrowSafe system that measures and records intakes and weights. The ranking by Residual feed intakes (RFI) identified those bulls that were most efficient regarding weight gains compared to their feed intakes. While there was a positive correlation between ADG and DMI (P = 0.011), there was no correlation between RFI and ADG. Relying simply on weight gains for breeding decisions is therefore not supported by this evidence. The daily feed intakes of the breed recorded (11.03 kg/d) were similar to those of non-native popular beef breeds, while the weight gains (0.95 kg/d) were smaller. Therefore, the selection for breeding of beef bulls could focus on feed efficiency and not only feed intakes or daily weight gains.

Vegetable breeding companies invest a considerable amount of their resources in phenotyping. The advancement of computer vision technology has made it possible to digitalize these processes, leading to improved efficiency and quality. However, phenotyping activities often take place in outdoor fields or greenhouses, where the environmental/illumination conditions are constantly changing. This lack of standardization presents a problem for automatically isolating the relevant elements in the images, which is an important first step for phenotyping. Classical image analysis methods have shown not to be robust enough for that in these changing conditions. However, in the last years, deep learning models have demonstrated to be able to identify and learn meaningful features that are more robust and representative of the underlying patterns, enabling them to handle diverse and changeable conditions effectively.

In this work, we propose a pepper instance segmentation solution based on deep learning after harvest under field conditions. We implement the method and validate it for three pepper varieties: Blocky Bell, Jalapeño and Lamuyo. We compare the performance of this new method for each variety with a previous solution based on classical image processing techniques, with the objective of measuring and demonstrating the superiority of deep learning-based instance segmentation over traditional methods as a first step for phenotyping.

The instance segmentation deep learning based models outperform the results obtained by classical image processing algorithms for the three pepper varieties: in Blocky Bell mAP is increased from 0.63 to 0.97, in Jalapeño from 0.39 to 0.52 and in Lamuyo from 0.67 to 0.97.