Search

Cereal crops play a critical role in global food security, but their productivity is increasingly threatened by climate change. This study evaluates the feasibility of using PlanetScope satellite imagery and a UAV equipped with the MicaSense RedEdge multispectral imaging sensor in monitoring winter wheat under various fertilizer treatments in a Mediterranean climate. Eleven fertilizer treatments, including organic-mineral fertilizer (OMF) pellets, were tested. The results show that conventional inorganic fertilization provided the highest yield (8618 kg ha⁻1), while yields from OMF showed a comparable performance to traditional fertilizers, indicating their potential for sustainable agriculture. PlanetScope data demonstrated moderate accuracy in predicting canopy cover (R2 = 0.68), crop yield (R2 = 0.54), and grain quality parameters such as protein content (R2 = 0.49), starch (R2 = 0.56), and hectoliter weight (R2 = 0.51). However, its coarser resolution limited its ability to capture finer treatment-induced variability. MicaSense, despite its higher spatial resolution, performed poorly in predicting crop components, with R2 values below 0.35 for yield and protein content. This study highlights the complementary use of remote sensing technologies to optimize wheat management and support climate-resilient agriculture through the integration of sustainable fertilization strategies. [ABSTRACT FROM AUTHOR]

High-flying insects that exploit tropospheric winds can disperse over far greater distances in a single generation than species restricted to below-canopy flight. However, the ecological consequences of such long-range dispersal remain poorly understood. For example, high-altitude dispersal may facilitate more rapid range shifts in these species and reduce their sensitivity to habitat fragmentation, in contrast to low-flying insects that rely more on terrestrial patch networks. Previous studies have primarily used surface-level variables with limited spatial coverage to explore dispersal timing and movement. In this study, we introduce a novel application of niche modelling to insect aeroecology by examining the relationship between a comprehensive set of atmospheric conditions and high-flying insect activity in the troposphere, as detected by weather surveillance radars (WSRs). We reveal correlations between large-scale dispersal events and atmospheric conditions, identifying key variables that influence dispersal behaviour. By incorporating high-altitude atmospheric conditions into niche models, we achieve significantly higher predictive accuracy compared with models based solely on surface-level conditions. Key predictive factors include the proportion of arable land, altitude, temperature, and relative humidity. [ABSTRACT FROM AUTHOR]

Regulation (EU) 2020/852 of the European Parliament, also known as the Taxonomy Regulation, facilitates environmentally sustainable investments. It is part of the concept of the European Green Deal and a 'tool' for financial institutions, enterprises, and investors, facilitating the assessment of the environmental impact of a particular project. The Regulation contains the criteria an activity must meet to be considered environmentally sustainable. The role of the Taxonomy Regulation is to enable the flow of public and private capital towards ecological and sustainable activities. The document does not need to be implemented into the legal order of individual EU member-states, which results in its direct application. The main financial instruments enabling the achievement of the goals of the Taxonomy Regulation may be green bonds and other forms of capital raising by entrepreneurs and forest ownership structures. The assumption of the Regulation is to achieve the principles of sustainable environmental activity when spending funds obtained from private investors. It is an issue of key significance to identify the areas of management and financial accounting in the operational activities of forest enterprises that can be qualified for the Taxonomy Regulation. Forestry activities, including the processes mentioned therein, the objectives of the New EU Forest Strategy, and the LULUCF Regulation, are to play an essential role in reducing greenhouse gas emissions. The role of forestry in the supply chain in its broad sense is also considered. Forestry and forest management can receive capital for sustainable development due to the threat resulting from exclusions that strengthen the protective function of the forest (the protection of biodiversity). These processes will occur at the expense of production and numerous social functions. [ABSTRACT FROM AUTHOR]

In recent years, the need to protect and conserve biodiversity has become more critical than ever before, as a prerequisite for both sustainable development and the very survival of the human species. This has made it a priority for the scientific community to develop technological solutions that provide data and information for monitoring, directly or indirectly, biodiversity and the drivers of change. A new era of satellite earth observation upgrades the potential of Remote Sensing (RS) to support, at relatively low cost, but with high accuracy the extraction of information over large areas, at regular intervals, and over extended periods of time. Also, the recent development of the Earth Observation Data Cubes (EODC) framework facilitates EO data management and information extraction, enabling the mapping and monitoring of temporal and spatial patterns on the Earth's surface. This submission presents the ELBIOS EODC, specifically developed to support the biodiversity management and conservation over Greece. Based on the Open Data Cube (ODC) framework, it exploits multi-spectral optical Copernicus Sentinel-2 data and provides a series of Satellite Earth Observation (SEO) biodiversity products and spectral indices nationwide. [ABSTRACT FROM AUTHOR]

Rice production remains highly dependent on nitrogen (N). There is no positive linear correlation between N concentration and yield in rice cultivation because an excess of N can unbalance the distribution of photo-assimilates in the plant and consequently produce a lower yield. We intended to study these imbalances. Remote sensing is a useful tool for monitoring rice crops. The purpose of this study was to evaluate the effectiveness of using remote sensing to assess the impact of N applications on rice crop behavior. An experiment with three different doses (120, 170 and 220 kg N·ha−1) was carried out over two years (2021 and 2022) in Valencia, Spain. Biomass, Leaf Area Index (LAI), plants per m2, yield, N concentration and N uptake were determined. Moreover, reflectance values in the green, red, and NIR bands of the Sentinel-2 satellite were acquired. The two data matrices were merged in a correlation study and the resulting interpretation ended in a protocol for the evaluation of the N effect during the main phenological stages. The positive effect of N on the measured parameters was observed in both years; however, in the second year, the correlations with the yield were low, being attributed to a complex interaction with climatic conditions. Yield dependence on N was optimally evaluated and monitored with Sentinel-2 data. Two separate relationships between NIR–red and NDVI–NIR were identified, suggesting that using remote sensing data can help enhance rice crop management by adjusting nitrogen input based on plant nitrogen concentration and yield estimates. This method has the potential to decrease nitrogen use and environmental pollution, promoting more sustainable rice cultivation practices. [ABSTRACT FROM AUTHOR]

In the UK uplands, prescribed burning of unenclosed heath, grass and blanket bog ('moorland') is used to support game shooting and grazing. Burning on moorland is contentious due to its impact on peat soils, hydrology and habitat condition. There is little information on spatial and temporal patterns of burning, the overlap with soil carbon and sensitive habitats and, importantly, whether these patterns are changing. This information is required to assess the sustainability of burning and the effectiveness of new legislation. We developed a method for semi‐automated detection of burning using satellite imagery – our best performing model has a balanced accuracy of 84.9%. We identified annual burn areas in Great Britain in five burning seasons from 2017/18 to 2021/22 of 8333 to 20 974 ha (average 15 250 ha year−1). Annual extent in England in 2021/22 was 73% lower than the average of the four previous seasons. Burning was identified over carbon‐rich soils (mean 5150 ha or 34% by area of all burning annually) and on steep slopes – 915 ha across the five seasons (1.3%), contravening guidance. Burning (>1 ha) was recorded in 14% of UK protected areas (PAs) and, within these, the percentage area of moorland burned varied from 2 to 31%. In England in some years, the percentage area of moorland burned inside PAs was higher than outside, while this was not the case in Scotland. Burning in sensitive alpine habitats totalled 158 ha across the five seasons. The reduction in burned area in England in 2021/22 could relate to England‐specific legislation, introduced in May 2021, to prohibit burning on deep peat in PAs. This suggests that regulation can be effective. However, the continued overlap with sensitive features suggests that burning falls short of sustainable practices. Our method will enable repeatable re‐assessment of burning extents and overlap with ecosystem services. [ABSTRACT FROM AUTHOR]

Low-intensity, diversified agricultural land use is needed to counteract the current decline in agrobiodiversity. Landscape ecology tools can support agrobiodiversity assessment efforts by investigating biodiversity-related ecological functions (pattern–process paradigm). In this study, we test a toolkit of landscape ecology analyses to compare different farm management models: polyculture agroforestry (POLY) vs. conventional monoculture crop management (CV). Farm-scale analyses are applied on temperate alluvial sites (Po Plain, Northern Italy), as part of a broader multi-scale analytical approach. We analyze the landscape ecological quality through landscape matrix composition, patch shape complexity, diversity, metastability, and connectivity indices. We assess farm differences through multivariate analyses and t-tests and test a farm classification tool, namely, a scoring system based on the relative contributions of POLY farms, considering their deviation from a local CV baseline. The results showed a separate ecological behavior of the two models. The POLY model showed better performance, with significant positive contributions to the forest and semi-natural component equipment and diversity; agricultural component diversity, metastability; total farm diversity, metastability, connectivity, and circuitry. A reference matrix for the ecological interpretation of the results is provided. Farm classification provides a quick synthesis of such contributions, facilitating farm comparisons. The methodology has a low cost and quickly provides information on ongoing ecological processes resulting from specific farm management practices; it is intended to complement field-scale assessments and could help to meet the need for a partially outcome-based assessment of good farm practice. [ABSTRACT FROM AUTHOR]

This review explores the integration of Artificial Intelligence (AI) with Sentinel-2 satellite data in the context of precision agriculture, specifically for crop yield estimation. The rapid advancements in remote sensing technology, particularly through Sentinel-2's high-resolution multispectral imagery, have transformed agricultural monitoring by providing critical data on plant health, soil moisture, and growth patterns. By leveraging Vegetation Indices (VIs) derived from these images, AI algorithms, including Machine Learning (ML) and Deep Learning (DL) models, can now predict crop yields with high accuracy. This paper reviews studies from the past five years that utilize Sentinel-2 and AI techniques to estimate yields for crops like wheat, maize, rice, and others. Various AI approaches are discussed, including Random Forests, Support Vector Machines (SVM), Convolutional Neural Networks (CNNs), and ensemble methods, all contributing to refined yield forecasts. The review identifies a notable gap in the standardization of methodologies, with researchers using different VIs and AI techniques for similar crops, leading to varied results. As such, this study emphasizes the need for comprehensive comparisons and more consistent methodologies in future research. The work underscores the significant role of Sentinel-2 and AI in advancing precision agriculture, offering valuable insights for future studies that aim to enhance sustainability and efficiency in crop management through advanced predictive models. [ABSTRACT FROM AUTHOR]

Remote sensing offers a low-cost method for estimating yields at large spatio-temporal scales. Here, we examined the ability of Sentinel-2 satellite imagery to map field-level maize yields across smallholder farms in two regions in Oromia district, Ethiopia. We evaluated how effectively different indices, the MTCI, GCVI, and NDVI, and different models, linear regression and random forest regression, can be used to map field-level yields. We also examined if models improved by adding weather and soil data and how generalizable our models were if trained in one region and applied to another region, where no data were used for model calibration. We found that random forest regression models that used monthly MTCI composites led to the highest yield prediction accuracies (R2 up to 0.63), particularly when using only localized data for training the model. These models were not very generalizable, especially when applied to regions that had significant haze remaining in the imagery. We also found that adding soil and weather data did little to improve model fit. Our results highlight the ability of Sentinel-2 imagery to map field-level yields in smallholder systems, though accuracies are limited in regions with high cloud cover and haze. [ABSTRACT FROM AUTHOR]

Grassland bird populations in the Mediterranean lowlands have declined dramatically over the past few decades. This decline is due to a combination of factors, including changes in land use and farming practices as well as the impacts of climate change. In particular, more intensive agricultural methods have played a significant role in this reduction. However, in the higher-altitude uplands of the region, traditional practices like pastoralism and rotational low-intensity farming are still common, and these areas continue to support substantial populations of several threatened grassland bird species. In this viewpoint, we discuss the challenges that the uplands are facing and suggest rethinking regional development to better balance the needs of people and nature. [ABSTRACT FROM AUTHOR]

Reliable and accurate crop yield prediction at the field scale is critical for meeting the global demand for reliable food sources. In this study, we tested the viability of VENμS satellite data as an alternative to other popular and publicly available multispectral satellite data to predict winter wheat yield and produce a yield prediction map for a field located in southwestern Ontario, Canada, in 2020. Random forest (RF) and support vector regression (SVR) were the two machine learning techniques employed. Our results indicate that machine learning models paired with vegetation indices (VIs) derived from VENμS imagery can accurately predict winter wheat yield 1~2 months prior to harvest, with the most accurate predictions achieved during the early fruit development stage. While both machine learning approaches were viable, SVR produced the most accurate prediction with an R2 of 0.86 and an RMSE of 0.3925 t/ha using data collected from tillering to the early fruit development stage. NDRE-1, NDRE-2, and REP from various growth stages were ranked among the top seven variables in terms of importance for the prediction. These findings provide valuable insights into using high-resolution satellites as tools for non-destructive yield potential analysis. [ABSTRACT FROM AUTHOR]

The escalating rates of deforestation, compounded by land degradation arising from intensified mining operations, forest fires, encroachments, and road infrastructure, among other factors, are severely disrupting the botanical and soil ecology of tropical ecosystems. This research focused on the upper Narmada River catchment area in central India, employing geospatial methodologies to assess land use and land cover (LULC) changes. Landsat 5, 7, and 8 satellite data for 2000, 2010, and 2022 were digitally classified using the maximum likelihood algorithm within the ERDAS IMAGINE and ArcGIS platforms. LULC was delineated into five categories (i.e., water bodies, built-up land, agricultural areas, forested regions, and fallow land). A spatio-temporal analysis revealed substantial declines of approximately 156 km2 in fallow land and 148 km2 in forested areas, accounting for 3.21% of the total area, while built-up land, water bodies, and agriculture land expanded between 2000 and 2022. There was a notable negative correlation observed between the Normalized Difference Vegetation Index (NDVI) and Land Surface Temperature (LST) across all LULC categories, except water bodies. The Land Degradation Vulnerability Index indicated that fallow lands, followed by forests and agriculture areas, exhibited a high vulnerability, with 43.16% of the landscape being categorized as vulnerable over the past 22 years. This study underscores the imperative of effective ecological restoration to mitigate land degradation processes and foster resilient ecosystems. The findings emphasize the importance of integrating scientific data into policy-making frameworks to ensure the comprehensive and timely management of the Narmada River landscape. [ABSTRACT FROM AUTHOR]

East African lakes support the food and water security of millions of people. Yet, a lack of continuous long-term water quality data for these waterbodies impedes their sustainable management. While satellite-based water quality retrieval methods have been developed for lakes globally, African lakes are typically underrepresented in training data, limiting the applicability of existing methods to the region. Hence, this study aimed to (1) assess the accuracy of existing and newly developed water quality band algorithms for East African lakes and (2) make satellite-derived water quality information easily accessible through a Google Earth Engine application (app), named LAndsat water QUality retrieval tool for east African lakes (LAQUA). We collated a dataset of existing and newly collected in situ surface water quality samples from seven lakes to develop and test Landsat water quality retrieval models. Twenty-one published algorithms were evaluated and compared with newly developed linear and quadratic regression models, to determine the most suitable Landsat band algorithms for chlorophyll-a, total suspended solids (TSS), and Secchi disk depth (SDD) for East African lakes. The three-band algorithm, parameterised using data for East African lakes, proved the most suitable for chlorophyll-a retrieval (R2 = 0.717, p < 0.001, RMSE = 22.917 μg/L), a novel index developed in this study, the Modified Suspended Matter Index (MSMI), was the most accurate for TSS retrieval (R2 = 0.822, p < 0.001, RMSE = 9.006 mg/L), and an existing global model was the most accurate for SDD estimation (R2 = 0.933, p < 0.001, RMSE = 0.073 m). The LAQUA app we developed provides easy access to the best performing retrieval models, facilitating the use of water quality information for management and evidence-informed policy making for East African lakes. [ABSTRACT FROM AUTHOR]

Capsule: In a 461 km2 unenclosed upland landscape in south-west England, long-term breeding Whinchat Saxicola rubetra persistence is more likely in areas characterized by a mixture of Bracken Pteridium aquilinum, ericaceous vegetation, and very low tree densities, situated in steep-sided valleys at mid-altitudes, further from agriculturally improved grassland or arable. Aims: To establish the correlates of Whinchat breeding territory retention between 1979 and 2015–2022 in a declining upland population. Methods: Historical Whinchat territories (identified in 1979) were revisited to assess range occupancy, producing a lost (n = 104) and retained (n = 60) sample. Territory retention probability was modelled at local (100 × 100 m) and broad (500 × 500 m) scales against remotely sensed data and field habitat data measured in 2022. Results: At the local scale, territory retention probability was greater in steeper valleys, further from arable or agriculturally improved grassland, peaked at five trees per ha in a quadratic response, and where Bracken cover was greater. Bracken cover effects were enhanced when ericaceous vegetation was also present. At the broad scale, retention probability was again greater in steeper valleys, with greater Bracken cover, and at very low tree densities in a quadratic response (but the latter was not important at the bottom of steep-sided valleys). Retention also peaked at around 350–400 m elevation in a quadratic response at the broad scale. Conclusions: In this population in south-west England, steep-sided valleys at 350–400 m, with a light scattering of trees, situated further from intensive enclosed farmland are more likely to retain Whinchats long term. Within these areas, a mixed Bracken and ericaceous field-layer should be encouraged, and blanket afforestation avoided, although lower densities of native trees appear to be more tolerated. [ABSTRACT FROM AUTHOR]

The combination of Remote Sensing and Deep Learning (DL) has brought about a revolution in converting digital surface models (DSMs) to digital terrain models (DTMs). DTMs are used in various fields, including environmental management, where they provide crucial topographical data to accurately model water flow and identify flood-prone areas. However, current DL-based methods require intensive data processing, limiting their efficiency and real-time use. To address these challenges, we have developed an innovative method that incorporates a physically informed autoencoder, embedding physical constraints to refine the extraction process. Our approach utilizes a normalized DSM (nDSM), which is updated by the autoencoder to enable DTM generation by defining the DTM as the difference between the DSM input and the updated nDSM. This approach reduces sensitivity to topographical variations, improving the model's generalizability. Furthermore, our framework innovates by using subtractive skip connections instead of traditional concatenative ones, improving the network's flexibility to adapt to terrain variations and significantly enhancing performance across diverse environments. Our novel approach demonstrates superior performance and adaptability compared to other versions of autoencoders across ten diverse datasets, including urban areas, mountainous regions, predominantly vegetation-covered landscapes, and a combination of these environments. [ABSTRACT FROM AUTHOR]

The UK breeding population estimate comprised 50,750 male Eurasian Woodcocks (95% CI: 42,935–59,251) in Britain and 937 males (95% CI: 274–1714) in Northern Ireland. The British population has continued to decline since 2013. To produce UK, British and regional estimates of breeding population size for Eurasian Woodcocks, and to assess the population change since 2003. The 2023 Breeding Woodcock Survey enlisted volunteer surveyors to count birds across a stratified sample of 1230 squares in England, Scotland, Wales, and Northern Ireland. The established 'roding count' methodology consists of up to three dusk visits, each lasting 75 min, during May and/or June. The results were used to calculate presence and mean density across 48 strata based on wooded area and regions, and extrapolated to produce regional and national estimates of population size. The population in Britain in 2023 was estimated at 50,750 male Woodcocks (95 CI: 42,935–59,251), representing an 8% decline since 2013, and a 35% decline since 2003. Despite small population increases in Wales and England since 2013, the continuing decline was driven by a 49.5% reduction in the population estimate for North Scotland. In 2023, Northern Ireland's breeding population of Eurasian Woodcocks was estimated at 937 males (95% CI: 274–1714), which is the first estimate produced using this species-specific method. Nationally, populations of Eurasian Woodcocks continue to decline, but the 2013–2023 declines were not as severe as those recorded between 2003 and 2013. The diverging population trends between North Scotland and the rest of Britain raise questions regarding regional variation in habitat suitability/availability and factors influencing overwinter survival. Recommendations are made for future versions of the Breeding Woodcock Survey regarding the composition of the random sample of squares, the treatment of incomplete data, and the sampling of non-woodland habitat. [ABSTRACT FROM AUTHOR]

The timely and robust prediction of wheat yield is very significant for grain trade and food security. In this study, the yield prediction model was developed by coupling an ensemble model with multi-source data, including vegetation indices (VIs) and meteorological data. The results showed that green chlorophyll vegetation index (GCVI) is the optimal remote sensing (RS) variable for predicting wheat yield compared with other VIs. The accuracy of the adaptive boosting- long short-term memory (AdaBoost-LSTM) ensemble model was higher than the LSTM model. AdaBoost-LSTM coupled with optimal input data had the best performance. The AdaBoost-LSTM model had strong robustness for predicting wheat yield under different irrigation and extreme weather events in general. Additionally, the accuracy of AdaBoost-LSTM for rainfed counties was higher than that for irrigation counties in most years except extreme years. The yield prediction model developed with the characteristic variables of the window from February to April had higher accuracy and smaller data requirements, which was the best prediction window. Therefore, wheat yield can be accurately predicted by the AdaBoost-LSTM model one to two months of lead time before maturity in the HHHP. Overall, the AdaBoost-LSTM model can achieve accurate and robust yield prediction in large-scale regions. [ABSTRACT FROM AUTHOR]

The increasing frequency and severity of UK wildfires, attributed in part to the effects of climate change, highlights the critical role of fuel moisture content (FMC) of live and dead vegetation in shaping wildfire behaviour. However, current models used to assess wildfire danger do not perform well in shrub-type fuels such as Calluna vulgaris, requiring in part an improved understanding of fuel moisture dynamics on diurnal and seasonal scales. To this end, 554 samples of upper live Calluna canopy, live Calluna stems, upper dead Calluna canopy, dead Calluna stems, moss, litter and organic layer (top 5 cm of organic material above mineral soil) were sampled hourly between 10:00 and 18:00 on seven days from March-August. Using a novel statistical method for investigating diurnal patterns, we found distinctive diurnal and seasonal trends in FMC for all fuel layers. Notably, significant diurnal patterns were evident in dead Calluna across nearly all sampled months, while diurnal trends in live Calluna canopy were pronounced in March, June, and August, coinciding with the peak occurrence of UK wildfires. In addition, the moisture content of moss and litter was found to fluctuate above and below their relative ignition thresholds throughout the day on some sampling days. These findings underscore the impact of diurnal FMC variations on wildfire danger during early spring and late summer in Calluna dominated peatlands and the need to consider such fluctuations in management and fire suppression strategies. [ABSTRACT FROM AUTHOR]

Accurate and timely monitoring of biochemical and biophysical traits associated with crop growth is essential for indicating crop growth status and yield prediction for precise field management. This study evaluated the application of three combinations of feature selection and machine learning regression techniques based on unmanned aerial vehicle (UAV) multispectral images for estimating the bio-parameters, including leaf area index (LAI), leaf chlorophyll content (LCC), and canopy chlorophyll content (CCC), at key growth stages of winter wheat. The performance of Support Vector Regression (SVR) in combination with Sequential Forward Selection (SFS) for the bio-parameters estimation was compared with that of Least Absolute Shrinkage and Selection Operator (LASSO) regression and Random Forest (RF) regression with internal feature selectors. A consumer-grade multispectral UAV was used to conduct four flight campaigns over a split-plot experimental field with various nitrogen fertilizer treatments during a growing season of winter wheat. Eighteen spectral variables were used as the input candidates for analyses against the three bio-parameters at four growth stages. Compared to LASSO and RF internal feature selectors, the SFS algorithm selects the least input variables for each crop bio-parameter model, which can reduce data redundancy while improving model efficiency. The results of the SFS-SVR method show better accuracy and robustness in predicting winter wheat bio-parameter traits during the four growth stages. The regression model developed based on SFS-SVR for LAI, LCC, and CCC, had the best predictive accuracy in terms of coefficients of determination (R2), root mean square error (RMSE) and relative predictive deviation (RPD) of 0.967, 0.225 and 4.905 at the early filling stage, 0.912, 2.711 μg/cm2 and 2.872 at the heading stage, and 0.968, 0.147 g/m2 and 5.279 at the booting stage, respectively. Furthermore, the spatial distributions in the retrieved winter wheat bio-parameter maps accurately depicted the application of the fertilization treatments across the experimental field, and further statistical analysis revealed the variations in the bio-parameters and yield under different nitrogen fertilization treatments. This study provides a reference for monitoring and estimating winter wheat bio-parameters based on UAV multispectral imagery during specific crop phenology periods. [ABSTRACT FROM AUTHOR]

Rural areas face profound challenges in transitioning towards sustainability. Intensive agriculture is deeply implicated in high greenhouse gas emissions, biodiversity decline and water pollution. As a more socio-economically heterogenous rural Europe emerges with a greater non-farming component, changes such as in-migration and tourism in some areas can also be seen to compromise sustainability, as can an ageing and declining population in others. The dominant means of European rural policy support has been direct income payments to farmers, with modest but increasing expectations of environmental cross-compliance over time. Since the early 1990s, new policy means have been introduced, many based around collaborative actions to enhance sustainability. These include the European Union (EU) Leader scheme, environmental cooperatives, catchment management projects and support for community renewable energy. These changes mark a shift from sectoral support to a more territorial and place-based policy, often built around collaborative partnership models. Scotland has developed a wide and distinctive range of communitarian policies to support sustainable rural development which connect to this territorial approach. This paper reviews the contribution of communitarian and collaborative policies to sustainability transitions, drawing primarily on Scottish policy but referencing these policies against policies in other developed economies. [ABSTRACT FROM AUTHOR]

This article addresses the challenges of water scarcity and climate change faced by cotton cultivation in the Xinjiang region of China. In response, a precise irrigation model based on reinforcement learning and the crop model DSSAT is proposed. The experimental site chosen for this study is Changji City in northwest China's Xinjiang province. Integrating the cotton model, CSM-CROPGRO, from the DSSAT model with reinforcement learning algorithms, a decision system was developed to provide accurate irrigation strategies that maximize cotton yield. The experimental results demonstrated that our approach significantly improved cotton yield and, compared to genetic algorithms, reduced water consumption while increasing production. This provides a better solution for developing cotton cultivation in the Xinjiang region. Additionally, we analyzed the differences in irrigation strategies among different decision scenarios, and the results showed that the reinforcement learning method achieved higher yields in water application trends during different periods. This research offers new ideas and methods for improving cotton-crop-management decisions. The study's focus on maximizing cotton yield while reducing water usage aligns with the sustainable management of water resources and the need for agricultural adaptation to changing climate conditions. It highlights the potential of reinforcement learning methods in improving irrigation decision-making and their applicability in addressing water scarcity challenges. This research contributes to the advancement of cotton crop management and provides valuable insights for agricultural decision-makers in the Xinjiang region and beyond. [ABSTRACT FROM AUTHOR]

Biomass burning (BB) as an important atmospheric carbon source has significant environmental and climatic influence. The frequent extreme BB cases in recent years have raised extensive concerns, yet the latest changes in BB emission on a global scale are not fully understood. Here, we systematically quantify the changes in BB carbon emission for 1999–2022 by fire types and on different scales based on the Global Fire Emissions Database with small fires (GFED4s) dataset. We find contrasting trends of savanna and boreal forest fires persistent over the study period, shaping the variation of global total BB carbon emission. The receding savanna fire drives a declining global BB carbon emission at −8 Tg C year−1 (−0.4% year−1) for 1999–2022, while an upturn of global carbon emission (5 Tg C year−1, 0.3% year−1) occurs in the recent decadal period (2008–2022) due to intensified boreal forest fires. The burned area decouples from carbon emission in terms of the changing tendency, as exhibited by the decreasing global burned area after 2008. Regionally, the fire carbon emission enhancement over the past 15 years (2008–2022) mainly comes from the boreal forests in northwestern North America, northeastern Siberia, and parts of the savanna area, all of which coincide with local climate change toward higher fire proneness. This study reveals a climate‐driven aggravation of the BB carbon emission, especially in high‐latitude boreal forests, and calls for attention to its potential impacts and effective fire management strategies. [ABSTRACT FROM AUTHOR]

With the rapid development of remote sensing technology, remote sensing products have found increasingly widespread applications across various fields. Nevertheless, as the volume of remote sensing image data continues to grow, traditional data retrieval techniques have encountered several challenges such as substantial query results, data overlap, and variations in data quality. Users need to manually browse and filter a large number of remote sensing datasets, which is a cumbersome and inefficient process. In order to cope with these problems of traditional remote sensing image retrieval methods, this paper proposes a remote sensing image retrieval algorithm for dense data (DD-RSIRA). The algorithm establishes evaluation metrics based on factors like imaging time, cloud coverage, and image coverage. The algorithm utilizes the global grids to create an ensemble coverage relation between images and grids. A locally optimal initial solution is obtained by a greedy algorithm, and then a local search is performed to search for the optimal solution by combining the strategies of weighted gain-loss scheme and novel mechanism. Ultimately, it achieves an optimal coverage of remote sensing images within the region of interest. In this paper, it is shown that the method obtains a smaller number of datasets with lower redundancy and higher data utilization and ensures the data quality to a certain extent in order to accurately meet the requirements of the regional coverage of remote sensing images. [ABSTRACT FROM AUTHOR]

Long time series land cover classification information is the basis for scientific research on urban sprawls, vegetation change, and the carbon cycle. The rapid development of cloud computing platforms such as the Google Earth Engine (GEE) and access to multi-source satellite imagery from Landsat and Sentinel-2 enables the application of machine learning algorithms for image classification. Here, we used the random forest algorithm to quickly achieve a time series land cover classification at different scales based on the fixed land classification sample points selected from images acquired in 2022, and the year-by-year spectral differences of the sample points. The classification accuracy was enhanced by using multi-source remote sensing data, such as synthetic aperture radar (SAR) and digital elevation model (DEM) data. The results showed that: (i) the maximum difference (threshold) of the sample points without land class change, determined by counting the sample points of each band of the Landsat time series from 1986 to 2022, was 0.25; (ii) the kappa coefficient and observed accuracy of the same sensor from Landsat 8 are higher than the results of the TM and ETM+ sensor data from 2013 to 2022; and (iii) the addition of a mining land cover type increases the kappa coefficient and overall accuracy mean values of the Sentinel 2 image classification for a complex mining and forest area. Among the land classifications via multi-source remote sensing, the combined variables of Spectral band + Index + Terrain + SAR result in the highest accuracy, but the overall improvement is limited. The method proposed is applicable to remotely sensed images at different scales and the use of sensors under complex terrain conditions. The use of the GEE cloud computing platform enabled the rapid analysis of remotely sensed data to produce land cover maps with high accuracy and a long time series. [ABSTRACT FROM AUTHOR]

Foliar feeding has been confirmed to be the fastest way of dealing with nutrient deficiencies and increasing the yield and quality of crop products. The synthesis of chlorophyll and photosynthesis are directly related to magnesium (Mg), which operates in the improvement of plant tissues and enhances the appearance of plants. This study aimed to analyze the correlation between two biophysical variables, including the leaf area index (LAI), the fraction of absorbed photosynthetically active radiation (FAPAR), and seven spectral vegetation indices. The spectral indices under investigation were Atmospherically Resistant Vegetation Index (ARVI), Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI), Disease–Water Stress Index (DSWI), Modified Chlorophyll Absorption Ratio Index (MCARI), the Red-Edge Inflection Point Index (REIP), and Pigment-Specific Simple Ratio (PSSRa). These indices were derived from Sentinel-2 data to investigate the impact of applying foliar applications of Mg from various sources in the production of green-onion crops. The biophysical variables were derived using field measurements and Sentinel-2 data under the effects of different sources of Mg foliar sprays. The correlation coefficient between field-measured LAI and remotely sensed, calculated LAI was 0.72 in two seasons. Concerning FAPAR, it was found that the correlation between remotely sensed calculated FAPAR and field-measured FAPAR was 0.66 in the first season and 0.89 in the second season. The magnesium oxide nanoparticle (nMgO) treatments resulted in significantly higher yields than the different treatments of foliar applications. The LAI and FAPAR variables showed a positive correlation with yield in the first season (October) and in the second season (March). Yield in treatment by nMgO varied significantly from that in the other treatments, ranging from 69-ton ha−1 in the first season to 74.9-ton ha−1 in the second season. Linear regression between LAI and PSSRa showed the highest correlation coefficient (0.90) compared with other vegetation indices in the first season. In the same season, the highest correlation coefficient (0.94) was found between FAPAR and PSSRa. In the second season, the highest accuracy to the estimate LAI was found in the correlation between MCARI and PSSRa, with correlation coefficients of 0.9 and 0.91, respectively. In the second season, the highest accuracy to the estimate FAPAR was found with the correlation between PSSRa, ARVI, and NDVI, with correlation coefficients 0.97 and 0.96, respectively. The highest correlation coefficients between vegetation indices and yield were found with ARVI and NDVI in the first season, and only with NDVI in the second season. [ABSTRACT FROM AUTHOR]

Land cover (LC) maps are used extensively for nature conservation and landscape planning, but low spatial resolution and coarse LC schemas typically limit their applicability to large, broadly defined habitats. In order to target smaller and more-specific habitats, LC maps must be developed at high resolution and fine class detail using automated methods that can efficiently scale to large areas of interest. In this work, we present a Machine Learning approach that addresses this challenge. First, we developed a multi-stage semantic segmentation approach that uses Convolutional Neural Networks (CNNs) to classify LC across the Peak District National Park (PDNP, 1439 km2) in the UK using a detailed, hierarchical LC schema. High-level classes were predicted with 95% accuracy and were subsequently used as masks to predict low-level classes with 72% to 92% accuracy. Next, we used these predictions to analyse the degree and distribution of fragmentation of one specific habitat—wet grassland and rush pasture—at the landscape scale in the PDNP. We found that fragmentation varied across areas designated as primary habitat, highlighting the importance of high-resolution LC maps provided by CNN-powered analysis for nature conservation. [ABSTRACT FROM AUTHOR]

The pressure of nutrient pollution derived from wastewater treatment works and agricultural runoff is a reason for the decline in the ecological health of aquatic habitats. Projected residential development in catchments creates further nutrient loading that can be offset by nutrient management solutions that maintain 'nutrient neutrality' either onsite or elsewhere within the same catchment. This study developed an export coefficient model in conjunction with detailed farm business data to explore a nature-based solution to nutrient neutrality involving seven scenarios of crop conversion to mixed woodland or grazing grass in an area of intensive arable cultivation in the groundwater-fed Blackwater sub-catchment of the River Wensum, UK. When compared with the monitored riverine export of nutrients, the calculated nitrogen (N) and phosphorus (P) inputs under current land use showed that subsurface denitrification is removing 48–78% of the leached N and that P is accumulating in the field soils. The addition of 235 residential homes planned for 2018–2038 in the Blackwater will generate an additional nutrient load of 190 kg N a−1 and 4.9 kg P a−1. In six of the seven scenarios, the modelled fractions of crop conversion (0.02–0.21) resulted in the required reduction in P loading and more than sufficient reduction in N loading (196–1874 kg a−1 for mixed woodland and 287–2103 kg a−1 for grazing grass), with the additional reduction in N load above the requirement for nutrient neutrality potentially contributing to further improvement in water quality. The cost of land conversion is modelled in terms of crop gross margins and nutrient credits generated in the form of 0.1 kg units of N or P. For the range of scenarios considered, the annual cost per credit ranged from GBP 0.78–11.50 for N for mixed woodland (GBP 0.74–7.85 for N for grazing grass) and from GBP 160–782 for P for both scenarios. It is concluded that crop conversion is a viable option to achieve nutrient neutrality in arable catchments in eastern England when considered together with other nutrient management solutions. [ABSTRACT FROM AUTHOR]

Winter wheat is a major food source for the inhabitants of North China. However, its yield is affected by drought stress during the growing period. Hence, it is necessary to develop drought-resistant winter wheat varieties. For breeding researchers, yield measurement, a crucial breeding indication, is costly, labor-intensive, and time-consuming. Therefore, in order to breed a drought-resistant variety of winter wheat in a short time, field plot scale crop yield estimation is essential. Unmanned aerial vehicles (UAVs) have developed into a reliable method for gathering crop canopy information in a non-destructive and time-efficient manner in recent years. This study aimed to evaluate strategies for estimating crop yield using multispectral (MS) and hyperspectral (HS) imagery derived from a UAV in single and multiple growth stages of winter wheat. To accomplish our objective, we constructed a simple linear regression model based on the single growth stages of booting, heading, flowering, filling, and maturation and a multiple regression model that combined these five growth stages to estimate winter wheat yield using 36 vegetation indices (VIs) calculated from UAV-based MS and HS imagery, respectively. After comparing these regression models, we came to the following conclusions: (1) the flowering stage of winter wheat showed the highest correlation with crop yield for both MS and HS imagery; (2) the VIs derived from the HS imagery performed better in terms of estimation accuracy than the VIs from the MS imagery; (3) the regression model that combined the information of five growth stages presented better accuracy than the one that considered the growth stages individually. The best estimation regression model for winter wheat yield in this study was the multiple linear regression model constructed by the VI of ' b 1 − b 2 / b 3 − b 4 ' derived from HS imagery, incorporating the five growth stages of booting, heading, flowering, filling, and maturation with r of 0.84 and RMSE of 0.69 t/ha. The corresponding central wavelengths were 782 nm, 874 nm, 762 nm, and 890 nm, respectively. Our study indicates that the multiple temporal VIs derived from UAV-based HS imagery are effective tools for breeding researchers to estimate winter wheat yield on a field plot scale. [ABSTRACT FROM AUTHOR]

Over the past few years, there has been extensive exploration of machine learning (ML), especially deep learning (DL), for crop yield prediction, resulting in impressive levels of accuracy. However, such models are highly dependent on training samples with ground truth labels (i.e., crop yield records), which are not available in some regions. Additionally, due to the existence of domain shifts between different spatial regions, DL models trained within one region (i.e., source domain) tend to have poor performance when directly applied to other regions (i.e., target domain). Unsupervised domain adaptation (UDA) has become a promising strategy to improve the transferability of DL models by aligning the feature distributions in the source domain and the target domain. Despite the success, existing UDA models generally assume an identical label space across different domains. This assumption can be invalid in crop yield prediction scenarios, as crop yields can vary significantly in heterogeneous regions. Due to the mismatch between label spaces, negative transfer may occur if the entire source and target domains are forced to align. To address this issue, we proposed a novel partial domain adversarial neural network (PDANN), which relaxes the assumption of fully, equally shared label spaces across domains by downweighing the outlier source samples. Specifically, during model training, the PDANN weighs each labeled source sample based on the likelihood of its yield value given the expected target yield distribution. Instead of aligning the target domain to the entire source domain, the PDANN model downweighs the outlier source samples and performs partial weighted alignment of the target domain to the source domain. As a result, the negative transfer caused by source samples in the outlier label space would be alleviated. In this study, we assessed the model's performance on predicting yields for two main commodities in the U.S., including corn and soybean, using the U.S. corn belt as the study region. The counties under study were divided into two distinct ecological zones and alternatively used as the source and target domains. Feature variables, including time-series vegetation indices (VIs) and sequential meteorological variables, were collected and aggregated at the county level. Next, the PDANN model was trained with the extracted features and corresponding crop yield records from the U.S. Department of Agriculture (USDA). Finally, the trained model was evaluated for three testing years from 2019 to 2021. The experimental results showed that the developed PDANN model had achieved a mean coefficient of determination (R2) of 0.70 and 0.67, respectively, in predicting corn and soybean yields, outperforming three other ML and UDA models by a large margin from 6% to 46%. As the first study performing partial domain adaptation for crop yield prediction, this research demonstrates a novel solution for addressing negative transfer and improving DL models' transferability on crop yield prediction. [ABSTRACT FROM AUTHOR]

Monitoring crop growth and estimating crop yield are essential for managing agricultural production, ensuring food security, and maintaining sustainable agricultural development. Combining the mechanistic framework of a crop growth model with remote sensing observations can provide a means of generating realistic and spatially detailed crop growth information that can facilitate accurate crop yield estimates at different scales. The main objective of this study was to develop a robust estimation methodology of within-field winter wheat yield at a high spatial resolution (20 m × 20 m) by combining a light use efficiency-based model and Sentinel-2 data. For this purpose, Sentinel-2 derived leaf area index (LAI) time series were assimilated into the Simple Algorithm for Yield Estimation (SAFY) model using an ensemble Kalman filter (EnKF). The study was conducted on rainfed winter wheat fields in southern Sweden. LAI was estimated using vegetation indices (VIs) derived from Sentinel-2 data with semi-empirical models. The enhanced two-band vegetation index (EVI2) was found to be a useful VI for LAI estimation, with a coefficient of determination (R2) and a root mean square error (RMSE) of 0.80 and 0.65 m2/m2, respectively. Our findings demonstrate that the assimilation of LAI derived from Sentinel-2 into the SAFY model using EnKF enhances the estimation of within-field spatial variability of winter wheat yield by 70% compared to the baseline simulation without the assimilation of remotely sensed data. Additionally, the assimilation of LAI improves the accuracy of winter wheat yield estimation by decreasing the RMSE by 53%. This study demonstrates an approach towards practical applications of freely accessible Sentinel-2 data and a crop growth model through data assimilation for fine-scale mapping of crop yield. Such information is critical for quantifying the yield gap at the field scale, and to aid the optimization of management practices to increase crop production. [ABSTRACT FROM AUTHOR]

Land-use maps are thematic materials reflecting the current situation, geographical diversity, and classification of land use and are an important scientific foundation that can assist decision-makers in adjusting land-use structures, agricultural zoning, regional planning, and territorial improvement according to local conditions. Spectral reflectance and radar signatures of time series are important in distinguishing land-use types. However, their impact on the accuracy of land-use mapping and decision making remains unclear. Also, the many spatial and temporal heterogeneous landscapes in southern Xinjiang limit the accuracy of existing land-use classification products. Therefore, our objective herein is to develop reliable land-use products for the highly heterogeneous environment of the southern Xinjiang Uygur Autonomous Region using the freely available public Sentinel image datasets. Specifically, to determine the effect of temporal features on classification, several classification scenarios with different temporal features were developed using multi-temporal Sentinel-1, Sentinel-2, and terrain data in order to assess the importance, contribution, and impact of different temporal features (spectral and radar) on land-use classification models and determine the optimal time for land-use classification. Furthermore, to determine the optimal method and parameters suitable for local land-use classification research, we evaluated and compared the performance of three decision-tree-related classifiers (classification and regression tree, random forest, and gradient tree boost) with respect to classifying land use. Yielding the highest average overall accuracy (95%), kappa (95%), and F1 score (98%), we determined that the gradient tree boost model was the most suitable for land-use classification. Of the four individual periods, the image features in autumn (25 September to 5 November) were the most accurate for all three classifiers in relation to identifying land-use classes. The results also show that the inclusion of multi-temporal image features consistently improves the classification of land-use products, with pre-summer (28 May–20 June) images providing the most significant improvement (the average OA, kappa, and F1 score of all the classifiers were improved by 6%, 7%, and 3%, respectively) and fall images the least (the average OA, kappa, and F1 score of all the classifiers were improved by 2%, 3%, and 2%, respectively). Overall, these analyses of how classifiers and image features affect land-use maps provide a reference for similar land-use classifications in highly heterogeneous areas. Moreover, these products are designed to describe the highly heterogeneous environments in the study area, for example, identifying pear trees that affect local economic development, and allow for the accurate mapping of alpine wetlands in the northwest. [ABSTRACT FROM AUTHOR]

Interspecific competition from introduced and naturally colonizing species has potential to affect resident populations, but demographic consequences for vertebrates have rarely been tested. We tested hypotheses of interspecific and intraspecific competition for density, body mass, and fertility of adult female Roe Deer (Capreolus capreolus) across a heterogeneous forest landscape occupied by two introduced deer species: Mediterranean Fallow Deer (Dama dama); and subtropical Reeve's Muntjac (Muntiacus reevesi). Species-specific deer densities in buffers around culling locations of 492 adult female Roe Deer, sampled over seven years, were extracted from spatially explicit models calibrated through annual nocturnal distance sampling. Roe Deer fertility and body mass were related to species-specific deer densities and extent of arable lands using piecewise structural equation models. Reeve's Muntjac density was lower at higher Fallow Deer densities, suggesting interspecific avoidance via interference competition, but greater when buffers included more arable land. Roe Deer body mass was marginally greater when buffers included more arable land and was independent of deer densities. However, Roe Deer fertility was unrelated to female body mass, suggesting that fertility benefits exceeded an asymptotic threshold of body condition in this low-density population. However, Roe Deer fertility was slightly greater rather than reduced in areas with greater local Roe Deer density, suggesting negligible intraspecific competition. In contrast, Roe Deer was less fertile in areas with greater Reeve's Muntjac densities; thus, interspecific exceeded intraspecific competition in this assemblage. In contrast, we found no support for any effects of Fallow Deer density on Roe Deer density, body mass, or fertility. Complex networks of interspecific competition operating in this deer assemblage include: interspecific interference from Fallow Deer exceeded habitat effects for Reeve's Muntjac; and interspecific competition from introduced, smaller sedentary Reeve's Muntjac reduced fertility, unlike intraspecific, or potential competition with larger, more mobile, Fallow Deer for native Roe Deer. Mechanisms driving Roe Deer fertility may include interspecific behavioral interference or stress–resource depletion is considered less likely because Roe Deer fertility was independent of body mass. Findings emphasize the importance of ensuring appropriate management strategies for controlling invasive species. [ABSTRACT FROM AUTHOR]

Forests cover approximately one-third of the Earth's land surface and constitute the core region of the carbon cycle on Earth. The paramount importance and multi-purpose applications of forest monitoring have gained widespread recognition over recent decades. Polarimetric synthetic aperture radar interferometry (PolInSAR) has been demonstrated as a promising technique to retrieve the forest height over large areas with a limited cost. This paper presents an overview of forest height inversion (FHI) techniques based on PolInSAR data. Firstly, we introduce the basic theories of PolInSAR and FHI procedures. Next, we review the established data-based algorithms for single-baseline data and describe innovative techniques related to multi-baseline data. Then, the model-based algorithms are also introduced with their corresponding forest scattering models under multiple data acquisition modes. Subsequently, a case study is presented to demonstrate the applicable scenarios and advantages of different algorithms. Model-based algorithms can provide accurate results when the scene and forest properties are well understood and the model assumptions are valid. Data-based algorithms, on the other hand, can handle complex scattering scenarios and are generally more robust to uncertainties in the input parameters. Finally, the prospect of forest height inversion was analyzed. It is our hope that this review will provide guidelines to future researchers to enhance further FHI algorithmic developments. [ABSTRACT FROM AUTHOR]

Promoting the transfer of rural residential land is paramount in enhancing the efficiency of its utilization. The willingness of farmers to transfer rural residential land is influenced by the number of permanent residents. Existing research has drawn different conclusions about the relationship between these two factors, but the differences have not been analyzed. This study is based on survey data collected from our field research in Deqing County, Zhejiang Province, and utilizes the Probit model and threshold effect model to investigate the role of per capita net income in the relationship between the number of permanent residents and the willingness to transfer rural residential land. The results indicate: (1) There is a non-linear impact of the number of permanent residents on the willingness of farmers who are willing to live in rural areas to transfer to their rural residential land with an income threshold. There is a non-linear impact of the number of permanent residents on the willingness of farmers who are willing to live in city areas to transfer out of their rural residential land, with two income thresholds. By comparing with the actual situation, the size and order of the thresholds are scientifically established. (2) The transfer of rural residential land can serve as a supplementary solution to individual household applications for rural residential land, addressing China's historical legacy issues concerning rural residential land. Considering these findings, policymakers should first actively promote the reform of the rural residential land system while ensuring safeguards for farmers and then work to increase the value of rural residential land. Additionally, they should implement differentiated policies to promote rural residential land transfer. This study can provide a valuable reference for effectively revitalizing idle rural residential land. [ABSTRACT FROM AUTHOR]

Declines in floral resources, pollen and nectar, are considered one cause of pollinator decline. However, the supply and demand of floral resources can vary temporally. In Britain, autumn has been suggested as a period of high floral resource availability due to the flowering of ivy (Hedera helix), a common native plant, combined with fewer insects active during this season. Here, we directly quantified the proportion of pollen and nectar produced by ivy, the primary autumn food source, which is uncollected by the flower‐visiting insect community.We quantified the proportion of nectar produced but uncollected by comparing the mass of nectar sugar accumulated in insect‐accessible versus inaccessible ivy flowers and by surveying the presence of wasted, crystalised, nectar on flowers. Pollen wastage was quantified by comparing pollen counts on anthers at the start of anthesis versus anthers dropped from ivy flowers.Approximately, half the floral resources, 59% nectar and 44% pollen, were uncollected by the flower‐visiting insect community in autumn. As ivy flowers supply most of the available nectar and pollen in autumn, our results show that a large proportion of all floral resources are wasted in autumn.Our results are the first to show that a season can be characterised by a large surplus of floral resources relative to collection by flower‐visiting insects. These results demonstrate the importance of considering seasonal variation in floral resources in the conservation of bees and other flower‐visiting insects. [ABSTRACT FROM AUTHOR]

Grassland aboveground biomass (AGB) is a crucial indicator when studying the carbon sink of grassland ecosystems. The exploration of the grassland AGB inversion method with viable reproducibility is significant for promoting the practicability and efficiency of grassland quantitative monitoring. Therefore, this study provides a novel retrieval method for grassland AGB by coupling the PROSAIL (PROSPECT + SAIL) model and the random forest (RF) model on the basis of the lookup-table (LUT) method. These sensitive spectral characteristics were optimized to significantly correlate with AGB (ranging from 0.41 to 0.68, p < 0.001). Four methods were coupled with the PROSAIL model to estimate grassland AGB in the West Ujimqin grassland, including the LUT method, partial least square (PLSR), RF and support vector machine (SVM) models. The ill-posed inverse problem of the PROSAIL model was alleviated using the MODIS products-based algorithm. Inversion results using sensitive spectral characteristics showed that the PROSAIL + RF model offered the best performance (R2 = 0.70, RMSE = 21.65 g/m2 and RMESr = 27.62%), followed by the LUT-based method, which was higher than the PROSAIL + PLSR model. Relatively speaking, the PROSAIL + SVM model was more challenging in this study. The proposed method exhibited strong robustness and universality for AGB estimation in large-scale grassland without field measurements. [ABSTRACT FROM AUTHOR]

One of the most valuable and nutritionally essential agricultural commodities worldwide is milk. The European Union and New Zealand are the second- and third-largest exporting regions of milk products and rely heavily on pasture-based production systems. They are comparable to the Australian systems investigated in this study. With projections of herd decline, increased milk yield must be obtained from a combination of animal genetics and feed efficiencies. Accurate pasture biomass estimation across all seasons will improve feed efficiency and increase the productivity of dairy farms; however, the existing time-consuming and manual methods of pasture measurement limit improvements to utilisation. In this study, Sentinel-2 (S2) band and spectral index (SI) information were coupled with the broad season and management-derived datasets using a Random Forest (RF) machine learning (ML) framework to develop a perennial ryegrass (PRG) biomass prediction model accurate to +/−500 kg DM/ha, and that could predict pasture yield above 3000 kg DM/ha. Measurements of PRG biomass were taken from 11 working dairy farms across southeastern Australia over 2019–2021. Of the 68 possible variables investigated, multiple simulations identified 12 S2 bands and 9 SI, management and season as the most important variables, where Short-Wave Infrared (SWIR) bands were the most influential in predicting pasture biomass above 4000 kg DM/ha. Conditional Latin Hypercube Sampling (cLHS) was used to split the dataset into 80% and 20% for model calibration and internal validation in addition to an entirely independent validation dataset. The combined internal model validation showed R2 = 0.90, LCCC = 0.72, RMSE = 439.49 kg DM/ha, NRMSE = 15.08, and the combined independent validation had R2 = 0.88, LCCC = 0.68, RMSE = 457.05 kg DM/ha, NRMSE = 19.83. The key findings of this study indicated that the data obtained from the S2 bands and SI were appropriate for making accurate estimations of PRG biomass. Furthermore, including SWIR bands significantly improved the model. Finally, by utilising an RF ML model, a single 'global' model can automate PRG biomass prediction with high accuracy across extensive regions of all seasons and types of farm management. [ABSTRACT FROM AUTHOR]

Accurate and timely acquisition of cropping intensity and spatial distribution of paddy rice is not only an important basis for monitoring growth and predicting yields, but also for ensuring food security and optimizing the agricultural production management system of cropland. However, due to the monsoon climate in southern China, it is cloudy and rainy throughout the year, which makes it difficult to obtain accurate information on rice cultivation based on optical time series images. Conventional image synthesis is prone to omission or redundancy of spectral and temporal features that are potentially important for rice-growth identification, making it difficult to determine the optimal features for high-precision mapping of paddy rice. To address these issues, we develop a method to granulate the effective use interval of classification features by extracting phenological signatures of rice to obtain cost-effective and highly accurate mapping results. Two steps are involved in this method: (1) analyzing the information on various features (spectra, polarization, and seasonal regularity) to identify three key phenological periods throughout the lifespan of paddy rice; (2) identifying the features with the highest class separation between paddy rice, non-paddy crops, and wetlands under different phenological stages; and (3) removing redundant features to retain the optimal feature combinations. Subsequently, the obtained feature sets are used as input data for the random forest classifier. The results showed that the overall accuracy of the identified rice results was 95.44% with F1 scores above 93% for both single- and double-cropping rice. Meanwhile, the correlation coefficient of our mapped rice area compared with the official statistics of rice area at county and district levels was 0.86. In addition, we found that combining Sentinel-1 and Sentinel-2 images for rice recognition was better than using Sentinel-1 or Sentinel-2 alone, and the classification accuracy was improved by 5.82% and 2.39%, which confirms that the synergistic Sentinel-1 and Sentinel-2 data can effectively overcome the problem of missing optical images caused by clouds and rain. Our study demonstrates the potential of distinguishing mixed rice-cropping systems in subtropical regions with fragmented rice-field distribution in a cloudy and rainy environment, and also provides a basis for the rational layout of rice production and improvement of cultivation systems. [ABSTRACT FROM AUTHOR]

The objectives of our survey were to determine the most important environmental factors within buffer zones that influenced mollusc communities and to evaluate the ecological conservation value of natural aquatic habitats (NAHs) that support mollusc species. Analysis of the spatial structure of buffer zones and catchments was based on a set of landscape metrics. Land cover classes were determined, and buffer zones within a radius of 500 m from a sampling point were marked out. Mollusc samples were collected from each NAHs. Our results showed that the number of patches and mean patch size were most associated with the distribution of mollusc species. Within patches of buffer zones, the length of the catchment boundaries with low-density housing, an increasing area of forest and pH of the water were also significant. Our results proved that landscape metrics provide essential information about catchment anthropogenic transformation. Therefore, landscape metrics and the designated buffer zones should be included in restoration plans for the river, water bodies and adjacent habitats as elements of modern, sustainable water management. NAHs located along a valley of a lowland river provide refuges for molluscs, play an essential role in the dispersal of IAS, create important protective biogeochemical barriers for rivers, constitute necessary sources of moisture and water and support microhabitats for distinct mollusc communities, especially in the context of global warming. [ABSTRACT FROM AUTHOR]