Search Results (541)

Despite increasing interest in including indigenous and local people in forest restoration initiatives, their views on which species are most useful, or reasons behind not planting native tree species are often ignored. Focused on south-western Rwanda, this study addressed these knowledge gaps. We carried out 12 focus group discussions with village elders to determine the following: main benefits provided by native forests, the native species they prefer for different uses, and the main barriers to species’ cultivation. Then, considering other key information from the literature, we performed a ranking exercise to determine which native species had the greatest potential for large-scale tree planting initiatives. Our results show that native forests provide 17 benefits to local communities, some of which cannot be replaced by plantations with exotic species. Among the 26 tree species identified as most useful for timber, firewood, medicine and fodder, ten were ranked as with the greatest potential for restoration initiatives. Of these, two had not been included in recent experimental plantations using native species in Rwanda, and none were considered among the priority species for domestication in Africa. Overall, our study highlights the need to better connect the ecological and social dimension of forest reforestation initiatives in multiple contexts. Full article

Aphis gossypii is a significant global pest that impacts numerous agricultural crops and vegetables, causing direct damage to food plants and indirect damage through the transmission of phytopathogenic viruses, primarily begomoviruses. In Panama, particularly in the Azuero region, viral infections transmitted by this aphid can affect a substantial share of tomato crops cultivated for industrial use. A traditional alternative to synthetic pesticides involves exploring plant extracts with insecticidal properties derived from wild plants found in our tropical forests, which can be easily prepared and applied by farmers. In this context, the present research aimed to evaluate the insecticidal activity of ethanolic extracts from the stems and leaves of Sphagneticola trilobata on both nymphs and adults of A. gossypii. Mortality was assessed at 24, 48, and 72 h after applying three doses of each extract (25, 50, and 100 µg/L). A standard phytochemical analysis to determine insecticidal activity revealed that both extracts exhibited significant efficacy at the highest concentration tested; however, the leaf extract demonstrated greater effectiveness at lower concentrations. A comprehensive metabolomic study indicated that the active compounds are diterpenes derived from the pimarenyl cation. These compounds have been extensively documented for their insecticidal potential against various insect species, suggesting that ethanolic extracts from this plant could serve as viable candidates for agricultural insecticides to combat aphid infestations. Full article

The value realization of forest ecological products (VRF) is crucial for rural revitalization, while the rural digital economy (RDE) plays a central role in enhancing farmers’ income (FI). This study constructs index systems to evaluate the RDE and VRF using the entropy weight method and the input–output model. Based on panel data from 31 Chinese provinces (2011–2021), we employ a comprehensive analytical framework that includes spatiotemporal evolution analysis, benchmark regression models, mediation effect analysis, and heterogeneity analysis. The results of the benchmark regression models show that the RDE significantly boosts FI, with each unit of increase in the RDE leading to a 2579-unit rise in income. Spatiotemporal evolution analysis reveals that the positive effect of the RDE weakens from the Eastern coastal regions to the less developed Western regions. Furthermore, mediation effect analysis indicates that VRF mediates the relationship between the RDE and FI. Heterogeneity analysis demonstrates that the impact of the RDE varies across regions and income levels. These findings provide strong evidence of the role of the RDE in promoting FI and highlight VRF as a mediating mechanism, offering policy insights for integrating digital and ecological strategies to foster inclusive rural growth. Full article

The development of a forestry carbon sink project is an important way to achieve carbon neutrality and carbon reduction, and the collective forest carbon sink project is an important part of China’s forestry carbon sink project. As the main management entity of collective forests, whether farmers are willing to produce forestry carbon sinks is directly related to the implementation effect of the project. In this paper, a partial equilibrium model of farmers’ forestry production behavior was established based on production function and utility function, and the path to enhance farmers’ willingness to produce forestry carbon sink through forestry carbon sink projects was analyzed in combination with forest ecological management theory. In terms of empirical analysis, the PSM-DID econometric model was established based on the survey data of LY in Zhejiang Province, China, and the following conclusions were drawn: (1) With the receipt of revenues from forestry carbon sequestration projects and partial cost-sharing by the government, farmers’ participation in forestry carbon sink projects can save investment in forest land management. (2) The saved forestry production costs and forestry carbon sink project subsidies can make up for the loss of farmers’ timber income, so that the net income of forestry will not be significantly reduced. (3) The forestry production factors saved by farmers can be transferred to non-agricultural sectors and increase non-agricultural net income, so that the net income of rural households participating in forestry carbon sink projects will increase. The forestry carbon sink project can improve the utility level of farmers and increase the willingness of farmers to produce forestry carbon sinks by delivering income to farmers and saving forestry production factors. This study demonstrates that a well-designed forestry carbon sink compensation mechanism, combined with an optimized allocation of production factors, can effectively enhance farmers’ willingness to participate. This insight is also applicable to countries or regions that rely on small-scale forestry operations. Full article

Community-Based Forest Management (CBFM) efforts are critical for sustainable natural resource governance in Northwest Ethiopia. This study investigated the various aspects of CBFM, emphasizing practical implementation in the context of the Awi Administrative Zone, Northwest Ethiopia. A structured questionnaire was handed out to 412 farmers across three districts—Dangila, Fagita Lokoma, and Banja. The quantitative data was analyzed using the Likert scale with SPSS version 23 software. Findings indicate that insufficient financial support (44%), limited community participation (30%), and weak institutional arrangements (19%) are the major factors impeding effective CBFM, with statistically significant regional variation (χ² = 242.8, df = 3, p = 0.000). On the other side, increased awareness and international support (34%) and enhanced local participation (36%) were the leading facilitators (χ² = 512.05, df = 11, p = 0.000). We look at the practical aspects of CBFM, from community-led conservation efforts to sustainable harvesting techniques, emphasizing the importance of indigenous knowledge alongside modern methodologies. The CBFM project in the northwest part of Ethiopia have facilitated biodiversity protection and environmental resilience by integrating local perspectives with broader developmental goals. However, obstacles such as land tenure, resource conflicts, and capacity restrictions continue, requiring adaptive methods and legislative reforms. This paper contributes to the ongoing discussion on sustainable natural resource management by offering empirical insights into the dynamics of CBFM in the Awi administrative zone of northwest Ethiopia. Full article

What is the potential impact on carbon storage of the native and introduced tree species commonly associated with coffee in the central Peruvian Amazon? Coffee is a pivotal crop within the Peruvian economy. Nevertheless, the establishment of new plantations—driven by the subsistence needs of smallholder farmers—has led to expansion into forested areas. Given the significance of this crop and the demonstrated ecosystem benefits of agroforestry systems (AFSs), the aim of this study was to evaluate the influence of native and introduced shade tree species on carbon storage in coffee plantations. This study was observational and exhibited characteristics of an unbalanced incomplete block design. Agroforestry systems (AFSs) with shade tree species such as Inga, Retrophyllum rospigliosii, Eucalyptus and Pinus, and three unshaded coffee plantations, were included in this study. The total carbon stored in each AFS was higher than in unshaded coffee plantations. Soil contributed between 47% and 91% to total carbon storage, shade trees (24–46%), coffee (2–7%), leaf litter (0.6–1.9%) and shrubs and herbaceous plants (0.02–0.3%). The AFS with R. rospigliosii achieved the highest carbon storage with 190.38 Mg ha⁻¹, highlighting the compatibility of this species with coffee plantations, as well as its positive effect on climate change mitigation in deforested areas. Full article

The accurate classification of banana ripeness is essential for optimising agricultural practices and enhancing food industry processes. This study investigates the classification of banana ripeness using Machine Learning (ML) and Deep Learning (DL) techniques. The dataset consisted of 1565 high-resolution images of bananas captured over a 20-day ripening period using a Canon EOS 90D camera under controlled lighting and background conditions. High-resolution images of bananas at different ripeness stages were classified into ‘unripe’, ‘ripe’, and ‘overripe’ categories. The training set consisted of 1398 images (89.33%), and the validation set consisted of 167 images (10.67%), allowing for robust model evaluation. Various ML models, including Decision Tree, Random Forest, KNN, SVM, CNN, and VGG models, were trained and evaluated for ripeness classification. Among these, DL models, particularly CNN and VGG, outperformed traditional ML algorithms, with the CNN and VGG achieving accuracy rates of 90.42% and 89.22%, respectively. These rates surpassed those of Decision Trees (71.86%), Random Forests (85.63%), KNNs (86.83%), and SVMs (89.22%). The study points out the importance of dataset quality, model selection, and preprocessing techniques in achieving accurate ripeness classification. Practical applications of these results include optimised harvesting practices, enhanced post-harvest handling, improved consumer experience, streamlined supply chain logistics, and automation in sorting systems. These results confirm the feasibility of using deep learning for the automated classification of ripening stages, with implications for reducing postharvest losses and improving supply chain logistics. These findings have significant implications for stakeholders in the banana industry, from farmers to consumers, and pave the way for the development of innovative solutions for banana ripeness classification. Full article

Balancing ecological conservation and rural livelihoods in protected areas remains a global challenge, particularly under strict land use regulations and economic development constraints. Territorial spatial planning (TSP) in an ecological function area (EFA) faces constraints such as land use restrictions, ecological redlines, and economic development limits. This study investigates how ecological land resources influence farmers’ incomes in ecological function areas (EFAs), with a focus on the moderating role of advanced livelihoods (ALI). Using an integrated Fixed-Effects–SVM–Genetic Algorithm framework, we quantify nonlinear policy-livelihood interactions and simulate multi-scenario governmental interventions (e.g., ecological investment, returning farmland to forest/RFF) across Beijing’s EFA, which can obtain the key findings as follows: (a) Ecological land resources have a significant positive effect on farmers’ incomes due to production-manner adjustment guided by governmental green strategy and corresponding TSP in an ecological restoration area of an EFA, while they have a non-significant impact in the core ecological reserve areas on account of the strict environmental protection restrictions on economic activities. (b) Differences in financial support between lower and higher economic development zones can bring about adverse impact results on farmers’ incomes in an EFA. (c) ALI significantly amplifies the positive impact of ecological land use on farmers’ incomes, demonstrating its critical role in bridging ecological and economic goals. (d) Sensitivity analysis results under RFF, targeted government investment, and ALI can maximize income gains through policy interaction from the government and farmer sides jointly. The above obtained results are beneficial to balance ecological protection and economic interests of farmers’ sustainably in an EFA. Full article

Soil moisture content (SMC) is a critical parameter for agricultural productivity, particularly in semi-arid regions, where irrigation practices are extensively used to offset water deficits and ensure decent yields. Yet, the socio-economic and remote context of these regions prevents sufficiently dense SMC monitoring in space and time to support farmers in their work to avoid unsustainable irrigation practices and preserve water resource availability. In this context, our study addresses the challenge of high spatial resolution (i.e., 20 m) SMC estimation by integrating remote sensing datasets in machine learning models. For this purpose, a dataset made of 166 soil samples’ SMC along with corresponding SMC, precipitation, and radar signal derived from Soil Moisture Active Passive (SMAP), Integrated Multi-satellitE Retrievals for GPM (IMERG), and Sentinel-1 (S1), respectively, was used to assess four machine learning models’ (Decision Tree—DT, Random Forest—RF, Gradient Boosting—GB, Extreme Gradient Boosting—XGB) reliability for SMC mapping. First, each model was trained/validated using only the coarse spatial resolution (i.e., 10 km) SMAP SMC and IMERG precipitation estimates as independent features, and, second, S1 information (i.e., 20 m) derived from single scenes and/or composite images was added as independent features to highlight the benefit of information (i.e., S1 information) for SMC mapping at high spatial resolution (i.e., 20 m). Results show that integrating S1 information from both single scenes and composite images to SMAP SMC and IMERG precipitation data significantly improves model reliability, as R² increased by 12% to 16%, while RMSE decreased by 10% to 18%, depending on the considered model (i.e., RF, XGB, DT, GB). Overall, all models provided reliable SMC estimates at 20 m spatial resolution, with the GB model performing the best (R² = 0.86, RMSE = 2.55%). Full article

Displaced abomasum (DA) is a digestive disorder that causes severe economic losses through the reduction in milk yield and early culling of cows. The predictive potential of DA-susceptible cases is of great importance to reduce economic losses. This study aimed for early prediction of DA. However, identifying cows at risk of DA can be difficult because DA is a complex trait and its incidence is low. For this purpose, in this study, the ability of five machine learning algorithms, namely Logistic Regression (LR), Naïve Bayes (NB), Decision Tree, Random Forest (RF) and Gradient Boosting Machines (GBM), to predict cases of DA was investigated. For these predictions, 20 herd–cow-specific features and sire genetic information from 7 Holstein dairy herds that calved between 2010 and 2020 were available. Model performance metrics indicated that GBM and RF algorithms outperformed the others in predicting DA with F2 measures of 0.32. The true positive rate in the RF was the highest compared to other methods at 0.75, followed by GBM at 0.70. Given the highly imbalanced data, this study showed the potential in forecasting cases susceptible to DA. This prediction tool can aid dairy farmers in making preventative management decisions by identifying cows susceptible to DA. Full article

Sugarcane yield prediction plays a pivotal role in enabling farmers to monitor crop development and optimize cultivation practices, guiding harvesting operations for sugar mills. In this study, we established three experimental fields, which were planted with three main sugarcane cultivars in Guangxi, China, respectively, implementing a multi-gradient fertilization design with 39 plots and 810 sampling grids. Multispectral imagery was acquired by unmanned aerial vehicles (UAVs) during five critical growth stages: mid-tillering (T1), late-tillering (T2), mid-elongation (T3), late-elongation (T4), and maturation (T5). Following rigorous image preprocessing (including stitching, geometric correction, and radiometric correction), 16 VIs were extracted. To identify yield-sensitive vegetation indices (VIs), a spectral feature selection criterion combining gray relational analysis and correlation analysis (GRD-r) was proposed. Subsequently, three supervised learning algorithms—Gradient Boosting Decision Tree (GBDT), Random Forest (RF), and Support Vector Machine (SVM)—were employed to develop both single-stage and multi-stage yield prediction models. Results demonstrated that multi-stage models consistently outperformed their single-stage counterparts. Among the single-stage models, the RF model using T3-stage features achieved the highest accuracy (R² = 0.78, RMSE_V = 7.47 t/hm²). The best performance among multi-stage models was obtained using a GBDT model constructed from a combination of DVI (T1), NDVI (T2), TDVI (T3), NDVI (T4), and SRPI (T5), yielding R² = 0.83 and RMSE_V = 6.63 t/hm². This study highlights the advantages of integrating multi-temporal spectral features and advanced machine learning techniques for improving sugarcane yield prediction, providing a theoretical foundation and practical guidance for precision agriculture and harvest logistics. Full article

Water security is a basic requirement of a region’s residents and also an important point of discussion worldwide. The middle route of the south-to-north water diversion project (MR-SNWDP) represents the most extensive inter-basin water allocation scheme globally. It is the major water resource for the Beijing–Tianjin–Hebei region, and its security is of great significance. In this study, 28 indicators including society, nature, and economy were selected from the water sources of the MR-SNWDP from 2000 to 2017. According to the Drivers-Pressures-States-Impact-Response (DPSIR) framework principle, the entropy weight method was used for weight calculation, and the comprehensive evaluation method was used for evaluating the water security of the water sources of the MR-SNWDP. This study showed that the total loss of nonpoint source pollution (NPSP) in the water source showed a trend of slow growth, except in 2007. Over the past 18 years, the proportion of pollution from three NPSP sources, livestock, and poultry (LP) breeding industry, planting industry, and living sources, were 44.56%, 40.33%, and 15.11%, respectively. The main driving force of water security in all the areas of the water source was the total net income per capita of farmers. The main pressure was the amount of LP breeding and the amount of fertilizer application. The largest impact indicators were NPSP gray water footprint and soil erosion area, and water conservancy investment was the most effective response measure. Overall, the state of the water source safety was relatively stable, showing an overall upward trend, and it had remained at Grade III except for in 2005, 2006, and 2011. The state of water safety in all areas except Shiyan City was relatively stable, where the state of water safety had fluctuated greatly. Based on the assessment findings, implications for policy and decision-making suggestions for sustainable management of the water sources of the MR-SNWDP resources are put forward. Agricultural cultivation in water source areas should reduce the application of chemical fertilizers and accelerate the promotion of agricultural intensification. Water source areas should minimize retail livestock and poultry farming and promote ecological agriculture. The government should increase investment in water conservancy and return farmland to forests and grasslands, and at the same time strengthen the education of farmers’ awareness of environmental protection. The evaluation system of this study combined indicators such as the impact of agricultural nonpoint source pollution on water bodies, which is innovative and provides a reference for the water safety evaluation system. Full article

The structural characteristics of hickory trees exhibit a significant correlation with their fruit yield. As a distinctive high-quality nut of Zhejiang Province, hickory is a unique high-end dry fruit and woody oil plant in China. However, the long growth cycle and extended maturation period make their management particularly challenging, especially in the absence of high-precision 3D digital models. This study aims to optimize hickory tree management and identify trees with the most optimal structural features. It employs gradient-boosted machine learning modeling based on 23 key tree characteristics, transforming the experiential knowledge of forest farmers into quantifiable parameters. The consensus model achieved an LOOCV average accuracy of 87%, a training set accuracy of 100%, and a test set accuracy of 78%. Through this approach, three structural parameters that significantly impact the hickory tree were identified: the number of branches, the total length of all branches, and the crown base height from the ground. These parameters were used to select trees with superior structural traits. Furthermore, a novel method based on distance metrics was developed to assess the structural similarity of trees. This research not only highlights the importance of incorporating tree structural characteristics into forest management practices but also demonstrates how modern technological tools can enhance the productivity and economic returns of hickory forests. Through this integration, both the sustainability and economic viability of hickory forests are improved. Full article

Climate change is threatening the sustainability of crop yields due to an increasing frequency of extreme weather conditions, requiring timely agricultural monitoring. Remote sensing facilitates consistent and continuous monitoring of field crops. This study aimed to estimate alfalfa crop height through satellite images and machine learning methods within the Google Earth Engine (GEE) Python API. Ground measurements for this study were collected over three years in four Canadian provinces. We utilized Sentinel-2 data to obtain satellite imagery corresponding to the same timeframe and location as the ground measurements. Three machine learning algorithms were employed to estimate plant height from satellite images: random forest (RF), support vector regression (SVR), and extreme gradient boosting (XGB). The efficacy of these algorithms has been assessed and compared. Several widely used vegetation indices, for instance normalized difference vegetation index (NDVI), enhanced vegetation index (EVI), and normalized difference red-edge (NDRE), were selected and assessed in this study. RF feature importance was utilized to determine the ranking of features from most to least significant. Several feature selection strategies were utilized and compared with the situation where all features are used. We demonstrated that RF and XGB surpassed SVR when assessing test data performance. Our findings showed that XGB and RF could predict alfalfa crop height with an R² of 0.79 and a mean absolute error (MAE) of around 4 cm Our findings indicated that SVR exhibited the lowest accuracy among the three algorithms tested, with R² of 0.69 and an MAE of 4.63 cm. The analysis of important features showed that normalized difference red edge (NDRE) and normalized difference water index (NDWI) were the most important variables in determining alfalfa crop height. The results of this study also demonstrated that using RF and feature selection strategies, alfalfa crop height can be estimated with comparably high accuracy. Given that the models were fully trained and developed in Python (v. 3.10), they can be readily implemented in a decision support system and deliver near real-time estimations of alfalfa crop height for farmers throughout Canada. Full article

In 1964, the National Forest Reserve Act (B.E. 2507) of Thailand classified all unoccupied forested areas as forest reserve, or pa sanguan. It became illegal to obtain individual land titles in forest reserves, thus reducing the land rights of farmers. In addition, roads could not be built, electricity access could not be provided, and agricultural support programs could not operate on land without land titles. However, in recent years, Thailand’s National Committee on Land Policy (Khana Kammakarn Natyobai Thidin Haeng Chat) has been promoting the Kor Tor Chor (KTC) program for communal land titling, designed to create land tenure clarity but not to provide full ownership rights. The objective of this article is to assess the vertical geographies associated with the KTC program in Nan Province, northern Thailand, and their implications with regard to land rights and accessing government funding, one of the key objectives of KTC. The article reveals that vertical land classification aspects associated with watershed classification present particular challenges to KTC. In particular, we argue that while farmers are generally happy with the benefits that have come to them due to KTC, vertical geographical circumstances have significantly influenced the abilities of village communities to benefit from the KTC program. Full article