Research Frontiers: Smart Agricultural Technology

What Drives Renewable Energy Adoption in EU Countries? Evidence on the Differential Effects of Economic, Structural and Energy Factors

Jităreanu Andy-Felix — 2026-08-25

The transition to renewable energy is a central objective of the European Union’s energy and climate policies, yet adoption rates differ significantly across Member States. This study analyses the economic, structural, and energy determinants of renewable energy adoption in the EU-27 over the period 2008–2023, using panel data models with country and year fixed effects and clustered standard errors. The results indicate that the relationship between renewable energy and its main determinants is limited and heterogeneous across countries. Most explanatory variables do not exhibit consistent and statistically significant effects across model specifications. In particular, research and development expenditure does not show a robust impact, while GDP per capita is associated with negative coefficients in several specifications, suggesting the presence of structural constraints and path dependency. Energy-related variables also display weak and unstable relationships. The findings suggest that renewable energy adoption is shaped by context-specific and heterogeneous dynamics rather than by uniform drivers. The study contributes by highlighting the limited explanatory power of standard macroeconomic indicators and supports the need for differentiated policy approaches across Member States.

Design and Test of the 1LFT-450D Variable Width Reversible Plough with Resistance Reduction Function

Aolong Geng — 2026-05-21

To address the issues of high working power consumption and poor structural stability of current ploughing equipment under conditions of straw coverage and heavy clay soil, a 1LFT-450D variable width reversible plough (VWRP) with resistance reduction function is designed. Based on the shark shield scale, a bionic resistance reduction plough body was designed. Through theoretical analysis, the turnover mechanism (TM) and the working width adjustment mechanism (WWAM) were designed, and their main structural parameters were determined. Further research was conducted on key components using simulation software. The discrete element method (DEM) simulation results indicated that arranging bionic ribs on the plough breast achieved the best resistance reduction effect compared with the ploughshare tip and ploughshare. Meanwhile, relative to the conventional plough body, the designed bionic plough body exhibited average reductions in resistance and energy consumption of 12.55% and 12.34%, respectively. The soil bin test further verified the resistance reduction performance of the designed bionic plough body. The kinematic performance of the TM and the WWAM was analyzed using RecurDyn, and their reliability and stability were verified through the mechanism performance test. The results of the field operation performance test showed that under the conditions of forward speed of 8–10 km·h⁻¹ and working width of 1320–2000 mm, the operation performance of the designed VWRP satisfied the requirements of relevant standards. This study can provide a theoretical reference for the resistance reduction optimization of agricultural machinery soil-engaging parts and the design of new ploughs.

Digitization of Field Rice Leaf Greenness (LCC 3 and 4) Using Drone-Based Remote Sensing and Machine Learning

Piyumi P. Dharmaratne — 2026-08-25

Precision monitoring of crops using drone or unmanned aerial vehicle (UAV) technology is rapidly growing as a climate-smart agriculture practice in rice farming systems in Sri Lanka and globally. In rice fields, the Leaf Color Chart (LCC) is traditionally used for manual comparison of a leaf to the standard LCC categories in the field to determine the fertilizer condition of the plant. However, this lacks autonomous monitoring, rapid monitoring of larger fields, scalability, and the digital transformation of the scores with sprayer drones for targeted fertilizer application. Drones with multispectral cameras could pose a greater rapid and digitalized solution for delineation of leaf color instead of LCC, in the field. Thus, this paper presents a novel attempt of digitization of conventional LCC levels 3 and 4, rice plant leaf greenness levels in the field, with classification and production of a spatial map using drone multispectral images and machine learning algorithms. The experimental setup consisted of ground sampling of LCC levels 3 and 4 from farmer fields and acquisition of drone imagery data above the field with a DJI Phantom 4 Multispectral
UAV, from which fifteen vegetation indices related to crop spectra were extracted. The vegetation indices were then employed for training (70%) and testing (30%) with machine learning algorithms: Random Forest (RF), as well as SVM-linear and SVM-RBF, focusing on LCC 3–4 class classification. The results showed good classification performance, with the RF algorithm reporting a test accuracy of 98.2%, outperforming SVM-linear (82.5%) and SVM-RBF (87.5%). The RF model outputs SR, EVI, MSR, NDVI, and TCARI as feature importance indices for the classification of LCC levels 3 and 4 in the rice field. The findings of this proposed method greatly encourage the adaptation of drone technology for real-time monitoring of rice leaf fertilizer levels linked to LCC levels three and four, and spatial identification of the zones across the field. This imposes greater advancement towards
climate-smart rice cultivation, targeted fertilizer application and rice field landscape pattern change analysis, underpinning the importance of field digitization.

Crop-IRM: An Intelligent Recognition and Management System for Organ Characteristics of Crop Germplasm Resources

Jie Zhang — 2026-08-24

The traditional methods of field-based phenotypic data collection for crop germplasm resources are often inefficient and highly subjective. As the foundation for breeding innovation, these resources require precise identification of phenotypic traits for effective evaluation and utilization. Therefore, efficient and standardized management of germplasm data is critical during the breeding process. To address this, we have developed an intelligent recognition and management system focused on the crop’s organ characteristics. The system consists of a web client for overall project management and data download, and a WeChat Mini Program for data collection and uploading. Both components are integrated with image analysis models. Using a soybean variety screening experiment as a case study, we have constructed multiple high-definition datasets for soybean phenotypic traits, and employed YOLOv11 series models for object detection, image classification, instance segmentation, and pose estimation to build analytical models for each of these traits. All models achieved a mean average precision (mAP@0.5) exceeding 94%, along with a top1_accuracy of 0.999. In practical evaluations, all models took between 0.71 and 3.03 s to make predictions for 100 images, achieving an accuracy rate of over 98%. This system delivers a comprehensive solution for field phenotypic identification of crop germplasm resources, substantially enhancing the efficiency and objectivity of data collection and analysis. It serves as a valuable decision-support tool for precision breeding and digital agriculture.

LASH-SegNet: A Lightweight Deep Learning Network for Multi-Trait Segmentation of Early-Stage Soybean Plants

Liqiang Qi — 2026-08-25

Accurate segmentation of multiple phenotypic traits in early-stage soybean plants is essential for automated phenotyping and early-stage breeding analysis. However, the morphological diversity and heterogeneous visual characteristics of key traits, including hypocotyls, flowers, pubescence, and leaves, make unified segmentation challenging under complex backgrounds. To address this problem, this study proposes LASH-SegNet, a lightweight deep learning network for multi-trait segmentation of early-stage soybean plants. The network integrates dynamic snake convolution to model elongated and non-rigid structures and incorporates a SegNeXt-Attention module to enhance multi-scale feature representation and boundary awareness. In addition, the WIoU_v3 loss function is adopted to improve localization accuracy and boundary alignment, particularly for slender targets. Experimental results show that LASH-SegNet achieves a precision of 88.82%, recall of 89.78%, and an F1-score of 89.30%, with an mAP50 of 91.24%, while maintaining a compact model size of 5.9 M parameters and 11.3 MB. These results demonstrate that LASH-SegNet provides an accurate and efficient solution for high-throughput multi-trait early-stage soybean plant phenotyping.