Search Results (160)

UAV remote sensing is widely used in the agricultural sector due to its non-destructive, rapid, and cost-effective advantages. This study utilized two years of field data with multisource fused imagery of soybeans to evaluate lodging conditions and investigate the impact of lodging grade information on yield prediction. Unlike traditional approaches that build empirical lodging models using band reflectance, vegetation indices, and texture features, this research introduces a transfer learning framework. This framework employs a ResNet18 encoder to directly extract features from raw images, bypassing the complexity of manual feature extraction processes. To address the imbalance in the lodging dataset, the Synthetic Minority Over-sampling Technique (SMOTE) strategy was employed in the feature space to balance the training set. The findings reveal that deep learning effectively extracts meaningful features from UAV imagery, outperforming traditional methods in lodging grade classification across all growth stages. On the 65 days after emergence (DAE), lodging grade classification using ResNet18 features achieved the highest accuracy (Accuracy = 0.76, recall = 0.76, F1 score = 0.73), significantly exceeding the performance of traditional methods. However, classification accuracy was relatively low in plots with higher lodging grades (lodging grades = 3, 5, 7), with an accuracy of 0.42 and an F1 score of 0.56. After applying the SMOTE module to balance the samples, the classification accuracy in plots with higher lodging grades improved to 0.65, marking an increase of 54.76%. To improve accuracy in yield prediction, this study integrates lodging information with other features, such as canopy spectral reflectance, vegetation indices, and texture features, using two multimodal data fusion strategies: input-level fusion (ResNet-EF) and intermediate-level fusion (ResNet-MF). The findings reveal that the intermediate-level fusion strategy consistently outperforms input-level fusion in yield prediction accuracy across all growth stages. Specifically, the intermediate-level fusion model incorporating measured lodging grade information achieved the highest prediction accuracy on the 85 DAE (R² = 0.65, RMSE = 529.56 kg/ha). Furthermore, when predicted lodging information was used, the model’s performance remained comparable to that of the measured lodging grades, underscoring the critical role of lodging factors in enhancing yield estimation accuracy. Full article

The NDVI is typically associated with medium-resolution images, e.g., Landsat imagery, and has often been linked to various agricultural parameters, except agricultural energy inputs. Thus, our objective was to analyze the performance of the NDVI associated with Landsat images to monitor both the evolution and impact of energy inputs on the spectral activity in some rural mountain crops. To do so, we studied energy inputs in three scenarios in the Ecuadorian Andes: high-mountain agroforestry systems (HAFSs), short-cycle production systems (SHCs), and low-mountain agroforestry systems (LAFSs). In 2022, information on energy inputs was collected for 415 systems (through field surveys). Using Google Earth Engine, we analyzed NDVI data associated with Landsat images between 2012 and 2023. Statistical analysis demonstrated significant positive correlations between energy inputs and the NDVI. As a novelty, this result means that energy inputs influence crops’ spectral activity. Furthermore, we demonstrated a historical enhancement of energy inputs across the inputs at the Landsat image scale. Therefore, further studies are needed to improve the resolution of this approach, for example, by integrating higher-resolution images to assess a more accurate NDVI response. Full article

Commercial tomato hybrids exhibit robust performance in modern high-input agricultural systems. However, their suitability for low-input farming remains uncertain. With the goal that by 2030, 25% of European agricultural production must be organic as part of the European Green Deal, this study aims to assess whether existing commercial tomato hybrids can offer a viable solution for low-input farming. Additionally, the impact of beneficial microorganisms such as plant growth-promoting rhizobacteria (PGPR), in relation to the growth and productivity of tomato hybrids under low-input cultivation is assessed. For this purpose, a well-defined microbial consortium, including Azotobacter chroococcum, Clostridium pasteurianum, Lactobacillus plantarum, Bacillus subtilis, and Acetobacter diazotrophicus, was applied as a liquid suspension to enhance root colonization and promote plant growth. Seven commercial tomatoes (Solanum lycopersicum L.) hybrids—the most popular in the Greek market—were evaluated for their performance under high-input (hydroponic) and low-input cultivation systems (with and without the use of PGPR). Several parameters related to yield, fruit quality, nutritional value, descriptive traits, and leaf elemental concentration were evaluated. In addition, a techno-economic analysis was conducted to assess whether hybrids developed under high-input conditions and intended for such cultivation environments suit low-input farming systems. The results indicated that such hybrids are not a viable, efficient, or profitable strategy for low-input cultivation. These findings underscore the importance of breeding tomato varieties, specifically adapted to low-input farming, highlighting the need for targeted breeding strategies to enhance sustainability and resilience in future agricultural systems. Notably, this study is among the first to comprehensively assess the response of commercial tomato hybrids under low-input conditions, addressing a critical gap in the current literature. Full article

Forest health monitoring at scale requires high-spatial-resolution remote sensing images coupled with deep learning image analysis methods. However, high-quality large-scale datasets are costly to acquire. To address this challenge, we explored the potential of freely available National Agricultural Imagery Program (NAIP) imagery. By comparing the performance of traditional convolutional neural network (CNN) models (U-Net and DeepLabv3+) with a state-of-the-art Vision Transformer (SegFormer), we aimed to determine the optimal approach for detecting unhealthy tree crowns (UTC) using a publicly available data source. Additionally, we investigated the impact of different spectral band combinations on model performance to identify the most effective configuration without incurring additional data acquisition costs. We explored various band combinations, including RGB, color infrared (CIR), vegetation indices (VIs), principal components (PC) of texture features (PCA), and spectral band with PC (RGBPC). Furthermore, we analyzed the uncertainty associated with potential subjective crown annotation and its impact on model evaluation. Our results demonstrated that the Vision Transformer-based model, SegFormer, outperforms traditional CNN-based models, particularly when trained on RGB images yielding an F1-score of 0.85. In contrast, DeepLabv3+ achieved F1-score of 0.82. Notably, PCA-based inputs yield reduced performance across all models, with U-Net producing particularly poor results (F1-score as low as 0.03). The uncertainty analysis indicated that the Intersection over Union (IoU) could fluctuate between 14.81% and 57.41%, while F1-scores ranged from 8.57% to 47.14%, reflecting the significant sensitivity of model performance to inconsistencies in ground truth annotations. In summary, this study demonstrates the feasibility of using publicly available NAIP imagery and advanced deep learning techniques to accurately detect unhealthy tree canopies. These findings highlight SegFormer’s superior ability to capture complex spatial patterns, even in relatively low-resolution (60 cm) datasets. Our findings underline the considerable influence of human annotation errors on model performance, emphasizing the need for standardized annotation guidelines and quality control measures. Full article

Some studies have shown that intensification improves the sustainability of bovine milk; however, this matter is controversial. The present study, performed in Southern Italy, in the Basilicata region, focuses on nine specialized dairy farms of the Marmo Platano internal area. These farms are characterized by a “low intensification profile”, and we estimated the sustainability of the Marmo Platano dairy system via life-cycle assessment using specific software. We chose 1 kg of refrigerated raw milk as the functional unit and four impact categories: global warming potential, non-renewable energy use, fossil depletion, and agricultural land occupation. All impact category values fell within the ranges in the bibliography. Economic allocation, a criterion led by the market value of milk and culled cows (and their ratio), significantly (p < 0.05) affected the global warming potential and agricultural land occupation of two farms (1.38 kg CO₂ eq and 2.48 m²y⁻¹ as the system mean), while it did not affect the fossil depletion of the entire system, i.e., 138 g of oil as the mean. After allocation, the system showed three different profiles (p < 0.05) of non-renewable energy use (average value 6.31 MJ), despite its closeness with fossil depletion. Despite the aptness of Marmo Platano, the animals are not grazed, whereas full barn housing ensures satisfactory milk yields. Mainly driven by its low input characteristics, implying a low culling rate, the system proved to be sustainable. Full article

Sacha inchi (Plukenetia volubilis), or the Inca peanut, is a promising functional food and sustainable alternative to traditional oilseed crops like soybean. Its seeds are rich in omega-3, omega-6, and omega-9 fatty acids, high-quality protein, and bioactive compounds, offering significant nutritional and health benefits. Moreover, sacha inchi cultivation thrives on degraded soils with minimal agrochemical input, supporting biodiversity and reducing environmental impacts. Despite its potential, its large-scale cultivation faces challenges such as genetic variability, low seed viability, and susceptibility to pests and diseases, resulting in inconsistent yields and plant quality. In vitro propagation presents a viable solution, enabling the production of genetically uniform, disease-free seedlings under controlled conditions. Successful in vitro cultivation depends on factors like explant selection, plant growth regulator combinations, medium composition, and environmental control. Advances in these techniques have improved propagation outcomes in other oilseed crops, such as enhanced germination, oil yield, and genetic stability, and offer similar opportunities for sacha inchi. By integrating in vitro and field techniques, this review highlights the potential of sacha inchi as a nutritionally rich, sustainable agricultural solution. These findings provide a foundation for advancing its cultivation, ensuring enhanced productivity, improved oil quality, and greater accessibility to its health benefits around the world. Full article

Over the past century, human activities have profoundly transformed global ecosystems. Lake Victoria in East Africa exemplifies these challenges, showcasing the interplay of anthropogenic pressures driven by land use changes, urbanization, agriculture, and industrialization. Our comprehensive study investigates polycyclic aromatic hydrocarbons (PAHs) and n-alkanes in the lake and its catchment to trace their sources and historical deposition. Sediment cores were collected from six sites within the catchment, representing diverse landforms and human activities, ensuring a comprehensive understanding of the basin. The results indicate significant spatial and temporal variations in both PAH and n-alkane profiles, reflecting diverse land use changes and development trajectories in the basin. Urban sites often exhibited higher concentrations of PAHs and short-chain n-alkanes, indicative of anthropogenic sources such as fossil fuel combustion, the input of petroleum hydrocarbons, and industrial emissions. In contrast, rural areas showed low PAH levels and a dominance of long-chain n-alkanes from terrestrial plant waxes. The n-alkane ratios, including the Carbon Preference Index and the Terrigenous–Aquatic Ratio, suggested shifts in organic matter sources over time, corresponding with land use changes and increased human activities. A mid-20th century shift toward increased anthropogenic contributions was observed across sites, coinciding with post-independence development. The mid-lake sediment core integrated inputs from multiple sub-catchments, providing a comprehensive record of basin-scale changes. These findings highlight three distinct periods of organic matter input: pre-1960s, dominated by natural and biogenic sources; 1960s–1990s, marked by increasing anthropogenic influence; and post-1990s, characterized by complex mixtures of pyrogenic, petrogenic, and biogenic sources. This study underscores the cumulative environmental and aquatic ecosystem effects of urbanization (rural vs. urban sites), industrialization, and land use changes over the past century. The combined analyses of PAHs and n-alkanes provide a comprehensive understanding of historical and ongoing environmental impacts, emphasizing the need for integrated management strategies that address pollutant inputs to preserve Lake Victoria’s ecological integrity. Full article

Current food production systems rely heavily on resource-poor small-scale farmers in the global south. Concomitantly, the agrifood systems are exacerbated by various a/biotic challenges, including low-input agriculture and climate crisis. The recent global food crisis further escalates the production and consumption challenges in the global market. With these challenges, coordinated efforts to address the world’s agrifood systems challenges have never been more urgent than now. This includes the implementation of deeply interconnected activities of food, land, and water systems and relationships among producers and consumers that operate across political boundaries. Nature-positive agriculture represents interventions both at the farm and landscape level that include a systems approach for the management of diverse issues across the land-water-food nexus. In the present article, we focus on the history of traditional farming and how it evolved into today’s nature-positive agriculture, including its limitations and opportunities. The review also explains the most impactful indicators for successful nature-positive agriculture, including sustainable management of soil, crops, seeds, pests, and mixed farming systems, including forages and livestock. Finally, the review explains the dynamics of nature-positive agriculture in the context of small-scale farming systems and how multilateral organizations like the CGIAR are converting this into transformative actions and impact. To address the climate crisis, CGIAR established the paradigm of nature-positive solutions as part of its research and development efforts aimed at transforming food, land, and water systems into more resilient and sustainable pathways. Full article

Agricultural production faces the dual challenge of increasing output while ensuring efficient resource utilization and environmental sustainability amid escalating global climate change and relentless increases in human demand. This study used provincial panel data from China from 2001 to 2022 to address these challenges. It systematically evaluated the dynamic evolution of agricultural green total factor productivity (AGTFP) by selecting “resources” and “energy” as core input factors and adopting a dual-output approach focused on “economic” and “low-carbon” outcomes. This study thoroughly analyzed the synergistic mechanisms of factors such as natural endowment, agricultural technology, economic development, and environmental regulation, exploring their impact on AGTFP enhancement through the innovative application of the dynamic fuzzy-set qualitative comparative analysis (fsQCA) method. There was a significant upward trend in AGTFP across China, indicating notable progress in green agricultural development. Additionally, three pathways promoting AGTFP improvement were identified: resource–economy-driven, technology–policy-guided, and multifactor-synergy. Simultaneously, two modes constraining AGTFP enhancement were uncovered: economy–policy suppression and human capital–economy suppression, highlighting the pivotal role of regional economic development and the conditionality of converting natural resource advantages. Moreover, the contributions of these pathways to AGTFP exhibited notable temporal dynamics. Major economic events, such as the 2008 financial crisis and policy shifts, including the 2012 “Ecological Civilization” strategy, significantly altered the effectiveness of existing configurations. Our analysis of regional heterogeneity revealed distinct geographical patterns, with the resource–economy-driven model predominantly observed in central regions and the technology–policy-guided and multi-factor-synergy models more prevalent in central and eastern regions. These findings highlight the importance of formulating differentiated policies tailored to the specific needs and stages of development in different regions. Specifically, enhancing the synergy between resource management and economic development, optimizing technology–policy integration, and promoting coordinated multisectoral development are critical to fostering sustainable agricultural practices. This research provides crucial empirical evidence for shaping targeted policies that can drive green agricultural development across diverse regional contexts. Full article

Modern agriculture requires substantial energy inputs, a significant portion of which are derived from fossil fuels. In the interests of addressing global challenges, such as sustainable resource management and reducing greenhouse gas emissions, this study examines changes in energy efficiency within Polish agriculture following the country’s accession to the European Union. It emphasizes the impact of dynamic structural transformations on energy consumption patterns in the agricultural sector. The research, based on data from Statistics Poland and FADN (Farm Accountancy Data Network) covering the period 2004–2021, analyzes various farm types and their economic sizes. Key indicators include energy intensity in agricultural production, expressed as the ratio of energy consumption to production value, and the share of different energy carriers in total energy inputs. The results demonstrate an overall improvement in energy efficiency during the analyzed period, with energy intensity decreasing by an average of 40%. The most significant improvements were observed in large-scale farms. Additionally, there was a notable decline in the use of solid fuels, offset by increased reliance on diesel fuel and electricity. Despite these positive trends, challenges persist. Energy costs per unit of production value in Poland remain relatively high compared to other EU countries, driven by rapidly rising energy prices and the structure of Polish agriculture, which predominantly produces goods with relatively low added value. Furthermore, variations in energy consumption structures across production types highlight the importance of specialization in enhancing energy efficiency at the farm level. Full article

The chemistry of atmospheric precipitation serves as an important proxy for discriminating the source(s) of air contaminants in urban environments as well as to discuss the dynamic of atmospheric chemistry exchanges. This approach can be undertaken at time scales varying from single events to seasonal and yearly time frames. Here, we characterized the chemical composition of two single rain episodes (18 July 2018 and 21 February 2019) collected in Wrocław (SW Poland). Our results demonstrated inner variations and seasonality (within the rain event as well as between summer and winter), both in ion concentrations as well as in their potential relations with local air contaminants and scavenging processes. Coupling statistical analysis of chemical parameters with meteorological/synoptic conditions and HYSPLIT back trajectories allowed us to identify three main factors (i.e., principal components; PC) controlling the chemical composition of precipitation, and that these fluctuated during each event: (i) PC1 (40%) was interpreted as reflecting the long-range transport and/or anthropogenic influences of emission sources that included biomass burning, fossil fuel combustion, industrial processes, and inputs of crustal origin; (ii) PC2 (20%) represents the dissolution of atmospheric CO₂ and HF into ionic forms; and (iii) PC3 (20%) originates from agricultural activities and/or biomass burning. Time variations during the rain events showed that each factor was more important at the start of the event. The study of both SO₄²⁻ and Ca²⁺ concentrations showed that while sea spray inputs fluctuated during both rain events, their overall impact was relatively low. Finally, below-cloud particle scavenging processes were only observed for PM₁₀ at the start of the winter rain episode, which was probably explained by the corresponding low rain intensity and an overlap from local aerosol emissions. Our study demonstrates the importance of multi-time scale approaches to explain the chemical variability in rainwater and both its relation to emission sources and the atmosphere operating processes. Full article

Considerable variation in soil often occurs within and across production fields, which can significantly impact farming input management strategies. Optimizing resource utilization while enhancing crop productivity is critical for achieving Sustainable Development Goals (SDGs). This paper proposes a low-cost retrofittable Variable Rate Applicator Controller (VRAC) designed to leverage soil variability and facilitate the adoption of Variable Rate Technologies. The controller operates using a Raspberry Pi platform, RTK—Global Navigation Satellite System (GNSS), a stepper motor, and an anti-slip wheel encoder. The VRAC allows precise, on-the-fly control of the Variable Rate application of farming inputs utilizing an accurate GNSS to pinpoint geographic coordinates in real time. A wheel encoder measures accurate distance travel, providing a real-time calculation of speed with a slip-resistant wheel design for precise RPM readings. The Raspberry Pi platform processes the data, enabling dynamic adjustments of variability based on predefined maps, while the motor driver controls the motor’s RPM. It is designed to be plug-and-play, user-friendly, and accessible for a broader range of farming practices, including seeding rates, dry fertilizer, and liquid fertilizer application. Data logging is performed from various field sensors. The controller exhibits an average of 0.864 s for rate changes from 267 to 45, 45 to 241, 241 to 128, 128 to 218, and 218 to 160 kg/ha at speeds of 8, 11, 16, 19, 24, and 32 km/h. It has an average coefficient of variation of 4.59, an accuracy of 97.17%, a root means square error (RMSE) of 4.57, an R square of 0.994, and an average standard deviation of 1.76 kg for seeding discharge. The cost-effectiveness and retrofitability of this technology offer an increase in precision agriculture adoption to a broader range of farmers and promote sustainable farming practices. Full article

Farmers have a pivotal responsibility in soil conservation: they can either preserve or deplete it through their choices. The responsibility of agriculture increases when practised in delicate ecosystems, such as lagoonal ones. The Venetian Lagoon islands, which are increasingly subjected to natural and anthropic subsidence, occasional flooding events (acqua alta), and eustatic sea level rise, are constantly exposed to erosive processes that challenge farmers to play with their adaptive capability. This research was carried out on the islands of Sant’Erasmo and Vignole, the most representative of island agriculture in the Venetian Lagoon: they almost exclusively rely on agriculture, which is almost nil in the other islands. This empirical research aimed to explore farmers’ agricultural practices, perceptions of soil changes, and how they adapt to them. It was fundamental for this study that the field research involved direct human contact with farmers (through semi-structured interviews) for data collection and using qualitative methods for data analysis, integrating scientific and non-scientific forms of knowledge and actors. The final purpose was to demonstrate the sustainability (valued on the potential depletion or regeneration capability) of agricultural practices and adaptation strategies on a theoretical basis. Despite their polycultural landscape (maintained by low-input farming systems), escaped from the predominant landscape oversimplification, Sant’Erasmo and Vignole are also subjected to unsustainable agricultural practices, including heavy mechanisation and synthetic inputs. Coupled with natural soil salinity that is exacerbated by increasing drought periods, these practices can contribute to soil degradation and increased salinity. The reported adaptation strategies, such as zeroed, reduced, or more conscious use of machines, were guided by the need to reduce the negative impact of soil changes on productivity. Our research revealed some of them as sustainable and others as unsustainable (such as increasing irrigation to contrast soil salinity). Participatory action research is needed to support farmers in designing effective sustainable agricultural practices and adaptation strategies. Full article

Soil erosion within agricultural landscapes has significant environmental and economic impacts and is strongly driven by reduced residue cover in agricultural fields. Large-area soil erosion models such as the Daily Erosion Project are important tools for understanding the patterns of soil erosion, but they rely on the accurate estimation of crop residue cover over large regions to infer the tillage practices, an erosion model input. Remote sensing analyses are becoming accepted as a reliable way to estimate crop residue cover, but most use localized training datasets that may not scale well outside small study areas. An alternative source of training data may be commonly conducted tillage surveys that capture information via rapid “windshield” surveys. In this study, we utilized the Google Earth Engine to assess the utility of three crop residue survey types (windshield tillage surveys, windshield binned residue surveys, and photo analysis surveys) and one synthetic survey (retroactively binned photo analysis data) as sources of training data for crop residue cover regressions. We found that neither windshield-based survey method was able to produce reliable regressions but that they can produce reasonable distinctions between low-residue and high-residue fields. On the other hand, both photo analysis and retroactively binned photo analysis survey data were able to produce reliable regressions with r² values of 0.57 and 0.56, respectively. Overall, this study demonstrates that photo analysis surveys are the most reliable dataset to use when creating crop residue cover models, but we also acknowledge that these surveys are expensive to conduct and suggest some ways these surveys could be made more efficient in the future. Full article

In the context of global and national carbon reduction targets, agricultural carbon emissions have become a critical focus. As global food demand increases, numerous agricultural policies have been implemented. Faced with limited policy resources, evaluating the impact of these policies on agricultural carbon emissions and production is essential. This study examined the relationship between food production and agricultural carbon emissions during the stage of agricultural development in Shandong Province, one of China’s major grain-producing regions, using the decoupling model. Additionally, the coupled coordination model was employed to assess the specific influence of agricultural policy clusters on this transformation. The results indicate that Shandong is transitioning from high-input, extensive farming to green, low-carbon, modern agriculture, with most cities shifting from strong negative decoupling to strong decoupling. Over time, the role of agricultural policies in driving this shift has grown more significant. Future policymaking should prioritize the overall quality of agricultural producers and maintain a continuous focus on sustainable, green development. Ensuring that policy directions align with evolving stages of agricultural development and adjusting them in real-time will be crucial. Full article