Coverage Path Planning (CPP) is a fundamental capability for agricultural robots; however, existing solutions often overlook energy constraints, resulting in incomplete operations in large-scale or resource-limited environments. This paper proposes an energy-aware CPP framework grounded in Soft Actor-Critic (SAC) reinforcement learning, designed for grid-based environments with obstacles and charging stations. To enable robust and adaptive decision-making under energy limitations, the framework integrates Convolutional Neural Networks (CNNs) for spatial feature extraction and Long Short-Term Memory (LSTM) networks for temporal dynamics. A dedicated reward function is designed to jointly optimize coverage efficiency, energy consumption, and return-to-base constraints. Experimental results demonstrate that the proposed approach consistently achieves over 90% coverage while ensuring energy safety, outperforming traditional heuristic algorithms such as Rapidly-exploring Random Tree (RRT), Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO) baselines by 13.4-19.5% in coverage and reducing constraint violations by 59.9-88.3%. These findings validate the proposed SAC-based framework as an effective and scalable solution for energy-constrained CPP in agricultural robotics.
Shalini Dangi, Surya Karthikeya Mullapudi, Chandravardhan Singh Raghaw
et al.
Precise yield prediction is essential for agricultural sustainability and food security. However, climate change complicates accurate yield prediction by affecting major factors such as weather conditions, soil fertility, and farm management systems. Advances in technology have played an essential role in overcoming these challenges by leveraging satellite monitoring and data analysis for precise yield estimation. Current methods rely on spatio-temporal data for predicting crop yield, but they often struggle with multi-spectral data, which is crucial for evaluating crop health and growth patterns. To resolve this challenge, we propose a novel Multi-Temporal Multi-Spectral Yield Prediction Network, MTMS-YieldNet, that integrates spectral data with spatio-temporal information to effectively capture the correlations and dependencies between them. While existing methods that rely on pre-trained models trained on general visual data, MTMS-YieldNet utilizes contrastive learning for feature discrimination during pre-training, focusing on capturing spatial-spectral patterns and spatio-temporal dependencies from remote sensing data. Both quantitative and qualitative assessments highlight the excellence of the proposed MTMS-YieldNet over seven existing state-of-the-art methods. MTMS-YieldNet achieves MAPE scores of 0.336 on Sentinel-1, 0.353 on Landsat-8, and an outstanding 0.331 on Sentinel-2, demonstrating effective yield prediction performance across diverse climatic and seasonal conditions. The outstanding performance of MTMS-YieldNet improves yield predictions and provides valuable insights that can assist farmers in making better decisions, potentially improving crop yields.
Albin Zeqiri, Julian Britten, Clara Schramm
et al.
Urban gardening is widely recognized for its numerous health and environmental benefits. However, the lack of suitable garden spaces, demanding daily schedules and limited gardening expertise present major roadblocks for citizens looking to engage in urban gardening. While prior research has explored smart home solutions to support urban gardeners, these approaches currently do not fully address these practical barriers. In this paper, we present PlantPal, a system that enables the cultivation of garden spaces irrespective of one's location, expertise level, or time constraints. PlantPal enables the shared operation of a precision agriculture robot (PAR) that is equipped with garden tools and a multi-camera system. Insights from a 3-week deployment (N=18) indicate that PlantPal facilitated the integration of gardening tasks into daily routines, fostered a sense of connection with one's field, and provided an engaging experience despite the remote setting. We contribute design considerations for future robot-assisted urban gardening concepts.
Large Multimodal Models (LMMs) has demonstrated capabilities across various domains, but comprehensive benchmarks for agricultural remote sensing (RS) remain scarce. Existing benchmarks designed for agricultural RS scenarios exhibit notable limitations, primarily in terms of insufficient scene diversity in the dataset and oversimplified task design. To bridge this gap, we introduce AgroMind, a comprehensive agricultural remote sensing benchmark covering four task dimensions: spatial perception, object understanding, scene understanding, and scene reasoning, with a total of 13 task types, ranging from crop identification and health monitoring to environmental analysis. We curate a high-quality evaluation set by integrating eight public datasets and one private farmland plot dataset, containing 27,247 QA pairs and 19,615 images. The pipeline begins with multi-source data pre-processing, including collection, format standardization, and annotation refinement. We then generate a diverse set of agriculturally relevant questions through the systematic definition of tasks. Finally, we employ LMMs for inference, generating responses, and performing detailed examinations. We evaluated 20 open-source LMMs and 4 closed-source models on AgroMind. Experiments reveal significant performance gaps, particularly in spatial reasoning and fine-grained recognition, it is notable that human performance lags behind several leading LMMs. By establishing a standardized evaluation framework for agricultural RS, AgroMind reveals the limitations of LMMs in domain knowledge and highlights critical challenges for future work. Data and code can be accessed at https://rssysu.github.io/AgroMind/.
Most research questions in agricultural and applied economics are of a causal nature, i.e., how one or more variables (e.g., policies, prices, the weather) affect one or more other variables (e.g., income, crop yields, pollution). Only some of these research questions can be studied experimentally. Most empirical studies in agricultural and applied economics thus rely on observational data. However, estimating causal effects with observational data requires appropriate research designs and a transparent discussion of all identifying assumptions, together with empirical evidence to assess the probability that they hold. This paper provides an overview of various approaches that are frequently used in agricultural and applied economics to estimate causal effects with observational data. It then provides advice and guidelines for agricultural and applied economists who are intending to estimate causal effects with observational data, e.g., how to assess and discuss the chosen identification strategies in their publications.
Rajhans Singh, Rafael Bidese Puhl, Kshitiz Dhakal
et al.
Deep learning models are transforming agricultural applications by enabling automated phenotyping, monitoring, and yield estimation. However, their effectiveness heavily depends on large amounts of annotated training data, which can be labor and time intensive. Recent advances in open-set object detection, particularly with models like Grounding-DINO, offer a potential solution to detect regions of interests based on text prompt input. Initial zero-shot experiments revealed challenges in crafting effective text prompts, especially for complex objects like individual leaves and visually similar classes. To address these limitations, we propose an efficient few-shot adaptation method that simplifies the Grounding-DINO architecture by removing the text encoder module (BERT) and introducing a randomly initialized trainable text embedding. This method achieves superior performance across multiple agricultural datasets, including plant-weed detection, plant counting, insect identification, fruit counting, and remote sensing tasks. Specifically, it demonstrates up to a $\sim24\%$ higher mAP than fully fine-tuned YOLO models on agricultural datasets and outperforms previous state-of-the-art methods by $\sim10\%$ in remote sensing, under few-shot learning conditions. Our method offers a promising solution for automating annotation and accelerating the development of specialized agricultural AI solutions.
In this study, the impact of research and development (R&D) expenditures on the value added of the agricultural sector in Iran was investigated for the period 1971-2021. For data analysis, the researchers utilized the ARDL econometric model and EViews software. The results indicated that R&D expenditures, both in the short and long run, have a significant positive effect on the value added in the agricultural sector. The estimated elasticity coefficient for R&D expenditures in the short run was 0.45 and in the long run was 0.35, indicating that with a 1 percent increase in research and development expenditures, the value added in the agricultural sector would increase by 0.45 percent in the short run and by 0.35 percent in the long run. Moreover, variables such as capital stock, number of employees in the agricultural sector, and working days also had a significant and positive effect on the value added in the agricultural sector.
Nicolas Soncini, Javier Cremona, Erica Vidal
et al.
We present a multi-modal dataset collected in a soybean crop field, comprising over two hours of recorded data from sensors such as stereo infrared camera, color camera, accelerometer, gyroscope, magnetometer, GNSS (Single Point Positioning, Real-Time Kinematic and Post-Processed Kinematic), and wheel odometry. This dataset captures key challenges inherent to robotics in agricultural environments, including variations in natural lighting, motion blur, rough terrain, and long, perceptually aliased sequences. By addressing these complexities, the dataset aims to support the development and benchmarking of advanced algorithms for localization, mapping, perception, and navigation in agricultural robotics. The platform and data collection system is designed to meet the key requirements for evaluating multi-modal SLAM systems, including hardware synchronization of sensors, 6-DOF ground truth and loops on long trajectories. We run multimodal state-of-the art SLAM methods on the dataset, showcasing the existing limitations in their application on agricultural settings. The dataset and utilities to work with it are released on https://cifasis.github.io/rosariov2/.
Abstract Background E2F/DP is a transcription factor family essential for regulating the cell cycle during plant growth, development, and stress response. However, its role in cotton, a crop of significant economic importance, particularly concerning salt tolerance, remains unexplored. Results We systematically identified 70 E2F/DP genes across four cotton species, including the allopolyploids Gossypium hirsutum and G. barbadense, as well as the parental diploids A-genome G. arboreum and D-genome G. raimondii. Phylogenetic analysis classified these genes into three subfamilies (E2F, DP, and DEL), with notable expansion of the E2F subfamily in tetraploid cotton through local duplication events rather than tandem duplication. Promoter analysis revealed enrichment of stress- and hormone-responsive cis-elements, suggesting functional roles in environmental adaptation. Tissue-specific and salt stress expression profiling highlighted GhDEL1_D08 as a key candidate, exhibiting rapid induction under salt stress. Functional validation using virus- induced gene silencing in cotton and overexpression in Arabidopsis thaliana demonstrated that GhDEL1_D08 negatively regulates salt tolerance by modulating antioxidant enzyme activities and membrane lipid peroxidation. Conclusions These findings provide a comprehensive view of the E2F/DP gene family in cotton and identify GhDEL1_D08 as a critical regulator of salt stress response, offering potential targets for breeding stress-resilient cotton varieties.
Ananditha Raghunath, Alexander Metzger, Hans Easton
et al.
Although farmers in Sub-Saharan Africa are accessing feature phones and smartphones at historically high rates, they face challenges finding a robust network of agricultural contacts. With collaborators, we conduct a quantitative survey of 1014 agricultural households in Kagera, Tanzania to characterize technology access, use, and comfort levels in the region. Recognizing the paucity of research on dual-platform technologies that cater to both feature phone and smartphone users, we develop and deploy eKichabi v2, a searchable directory of 9833 agriculture-related enterprises accessible via a USSD application and an Android application. To bridge the gap in affordances between the two applications, we conduct a mixed methods pilot leveraging mobile money agents as intermediators for our USSD application's users. Through our investigations, we identify the advantages, obstacles, and critical considerations in the design, implementation, and scalability of agricultural information systems tailored to both feature phone and smartphone users in Sub-Saharan Africa.
Muhammad Waseem Akram, Marco Vannucci, Giorgio Buttazzo
et al.
The leaf area index determines crop health and growth. Traditional methods for calculating it are time-consuming, destructive, costly, and limited to a scale. In this study, we automate the index estimation method using drone image data of grapevine plants and a machine learning model. Traditional feature extraction and deep learning methods are used to obtain helpful information from the data and enhance the performance of the different machine learning models employed for the leaf area index prediction. The results showed that deep learning based feature extraction is more effective than traditional methods. The new approach is a significant improvement over old methods, offering a faster, non-destructive, and cost-effective leaf area index calculation, which enhances precision agriculture practices.
Pasquale De Marinis, Gennaro Vessio, Giovanna Castellano
Precision agriculture relies heavily on effective weed management to ensure robust crop yields. This study presents RoWeeder, an innovative framework for unsupervised weed mapping that combines crop-row detection with a noise-resilient deep learning model. By leveraging crop-row information to create a pseudo-ground truth, our method trains a lightweight deep learning model capable of distinguishing between crops and weeds, even in the presence of noisy data. Evaluated on the WeedMap dataset, RoWeeder achieves an F1 score of 75.3, outperforming several baselines. Comprehensive ablation studies further validated the model's performance. By integrating RoWeeder with drone technology, farmers can conduct real-time aerial surveys, enabling precise weed management across large fields. The code is available at: \url{https://github.com/pasqualedem/RoWeeder}.
Hanzhe Teng, Yipeng Wang, Dimitrios Chatziparaschis
et al.
Unmanned and intelligent agricultural systems are crucial for enhancing agricultural efficiency and for helping mitigate the effect of labor shortage. However, unlike urban environments, agricultural fields impose distinct and unique challenges on autonomous robotic systems, such as the unstructured and dynamic nature of the environment, the rough and uneven terrain, and the resulting non-smooth robot motion. To address these challenges, this work introduces an adaptive LiDAR odometry and mapping framework tailored for autonomous agricultural mobile robots operating in complex agricultural environments. The proposed framework consists of a robust LiDAR odometry algorithm based on dense Generalized-ICP scan matching, and an adaptive mapping module that considers motion stability and point cloud consistency for selective map updates. The key design principle of this framework is to prioritize the incremental consistency of the map by rejecting motion-distorted points and sparse dynamic objects, which in turn leads to high accuracy in odometry estimated from scan matching against the map. The effectiveness of the proposed method is validated via extensive evaluation against state-of-the-art methods on field datasets collected in real-world agricultural environments featuring various planting types, terrain types, and robot motion profiles. Results demonstrate that our method can achieve accurate odometry estimation and mapping results consistently and robustly across diverse agricultural settings, whereas other methods are sensitive to abrupt robot motion and accumulated drift in unstructured environments. Further, the computational efficiency of our method is competitive compared with other methods. The source code of the developed method and the associated field dataset are publicly available at https://github.com/UCR-Robotics/AG-LOAM.
Lamiaa Hassan, Ibrahem M. A. Hasan, Zeinab Al-Amgad
et al.
Copper oxide nanoparticles (CuO NPs) are metallic nanoparticles fulfilling several functions such
as good conductivity, catalyst, used in sensors and energy storage devices, and antibacterial
characteristics. However, the cytotoxicity and particular mechanisms of exposure to CuO NPs on
male testicular function are still elusive. In the current study, seventy-five mature male albino rats
received single doses of 0, 100, 200, 1000, and 2000 mg/kg CuO NPs by oral gavage. Blood and
epididymal semen as well as testicular tissue were collected 2, 8, and 15 days after administration.
Serum testosterone level, sperm motility, count, morphology, viability, and gonadosomatic index
(GSI) were assessed at the same time; histological structure of the testes was examined. The result
revealed that CuO NPs significantly reduced serum testosterone levels, suppressed sperm
concentration, and significantly elevated abnormal and dead sperm percent. Furthermore, testicular
tissue showed degeneration of germ, Sertoli, Leydig cells, and spermatocytes with the incidence of
vacuolation and inflammatory cell infiltration. In conclusion, CuO NPs exert adverse and
irreversible effects on testicular function and sperm physiological characteristics; these harmful
effects were markedly observed after administration of high doses of CuO NPs.
The advent of large language models (LLMs) has heightened interest in their potential for multimodal applications that integrate language and vision. This paper explores the capabilities of GPT-4V in the realms of geography, environmental science, agriculture, and urban planning by evaluating its performance across a variety of tasks. Data sources comprise satellite imagery, aerial photos, ground-level images, field images, and public datasets. The model is evaluated on a series of tasks including geo-localization, textual data extraction from maps, remote sensing image classification, visual question answering, crop type identification, disease/pest/weed recognition, chicken behavior analysis, agricultural object counting, urban planning knowledge question answering, and plan generation. The results indicate the potential of GPT-4V in geo-localization, land cover classification, visual question answering, and basic image understanding. However, there are limitations in several tasks requiring fine-grained recognition and precise counting. While zero-shot learning shows promise, performance varies across problem domains and image complexities. The work provides novel insights into GPT-4V's capabilities and limitations for real-world geospatial, environmental, agricultural, and urban planning challenges. Further research should focus on augmenting the model's knowledge and reasoning for specialized domains through expanded training. Overall, the analysis demonstrates foundational multimodal intelligence, highlighting the potential of multimodal foundation models (FMs) to advance interdisciplinary applications at the nexus of computer vision and language.
Nelly Centurión, Ignacio Mariscal-Sancho, Mariela Navas
et al.
Legumes provide important benefits in rotations. Interseeding cover crops (CCs) allows an additional legume CC in case of a short window after the main crop. However, legume input level and management could modify the expected benefits. In a Mediterranean irrigated agroecosystem, we evaluated the responses of topsoil (0–10 cm) and early maize development to increasing legume CC input in a biannual maize–wheat rotation under traditional tillage (TT; CC incorporated) and minimum tillage (MT; CC rolled-crimped). In the third year, at two early maize stages, we tested three legume input levels: (i) R0, non-CC; (ii) R1, barley–vetch CC; (iii) R2, vetch interseeded into maize in addition to the CC mixture. Overall, MT enhanced soil properties, but frequently conditioned to legume input level. The tillage system affected R1 the most, with MTR1 showing the better overall soil response while TTR0 showed the poorest. MTR2 was the best combination for early maize development, but not for soil health. Moreover, a better overall soil health did not lead to a better early maize performance in the short term. In this alkaline soil, CC favored early maize growth, whereas mycorrhization, enhanced under TT, favored crop nutrition. Increased legume input under MT should be monitored to avoid negative effects in soil in the mid–long term.
Anne-Marieke C. Smid, Vanessa Boone, Melanie Jarbeau
et al.
ABSTRACT: Dairy cows are highly motivated to access pasture and have a partial preference for alternative forms of outdoor access (e.g., deep-bedded outdoor sand or wood-chip packs). In addition, Canadians value the provision of outdoor access to dairy cows as they perceive it as important for good cow welfare. In contrast to Europe, Oceania, and the United States, little data exist on the use of outdoor access on Canadian dairy farms. Therefore, our objective was to assess current outdoor access practices for dairy cows in Canada. An online questionnaire was used to determine housing and outdoor access practices for lactating cows, dry cows, pregnant heifers, and weaned, nonpregnant heifers on Canadian dairy farms. The questionnaire was distributed by the 10 provincial milk boards between November 2020 and August 2021, resulting in an 8.9% response rate (n = 903 completed questionnaires). In total, 75% (n = 675) of respondents provided some form of outdoor access to at least 1 cattle class on their farm. Pasture was the most frequently used form of outdoor access for all cattle classes. Based on a weighted average, a total of 29% and 48% of Canadian dairy farms provided lactating and dry cows, respectively, access to pasture; for youngstock, these numbers were 48% and 27% for pregnant heifers and weaned, nonpregnant heifers, respectively. Herd size (for each cow class), indoor housing system, and region were all associated with the provision of pasture. Farms with larger lactating herds less often provided access to pasture; larger herd sizes in terms of weaned, nonpregnant heifers, pregnant heifers, and dry cows were also associated with a lower likelihood of access to pasture. Farms using indoor bedded pack housing for their lactating cows more often provided pasture to this cattle class than farms with freestall or tiestall housing; this likelihood did not differ between farms with tie or freestall housing for this cattle class. Dry cows or pregnant heifers housed in a tiestall were more often provided pasture than freestall-housed dry cows or pregnant heifers. Housing type for weaned, nonpregnant heifers was not associated with the likelihood of pasture provision. Farms in British Columbia or on Canada's East Coast (i.e., Nova Scotia, New Brunswick, and Prince Edward Island) more often provided lactating cows pasture compared with farms in other regions. For the other 3 cattle classes, farms on the East Coast of Canada more often provided pasture than farms in other parts of Canada. These results will inform future decisions regarding outdoor access for Canadian dairy cattle and may also aid in identifying future areas of research. For example, our results may aid in designing housing systems that facilitate outdoor access in larger herds and in areas that are subject to more extreme weather conditions.