Over the last few years, intensive agriculture has often been denounced as a source of negative effects, particularly at the environmental and health level (overexploitation of natural resources, degradation of their quality, appearance and development of several diseases, etc.). Reducing the excessive use of agricultural inputs for the protection of the environment and the preservation of human and animal health is a social requirement nowadays. Investing in more sustainable agricultural models which make it possible to reduce, or even eliminate the risks, has become urgent. A possible solution may be to resort to agroecological systems. In order to be sustainable, these new systems must be performant at the agronomic, economic, social, and environmental levels. There is a multitude of tools for assessing the sustainability of agricultural systems. These tools are inappropriate for organic and agroecological systems, and do not make it possible to measure the agroecological transition performance of farms (Trabelsi et al. Environ Sci Pollut Res 23:139-156, 2016; Trabelsi 2017). This research project aims to design a decision support tool in order to help farms throughout the agroecological transition process, to assess the performance of this transition, and to put forward improvement scenarios. Contrary to other assessment methods, ESSIMAGE (Evaluation and Simulation of Agroecological Systems) is based on both pressure and impact indicators, and takes the specificities of agricultural production systems into account. It is a dynamic tool which not only makes it possible to assess farm performance at the present moment but also to consider the future by putting forward possible alternative improvement scenarios and by simulating their consequences at a later stage. ESSIMAGE is based on the interaction of two elements: agro-environmental, social, and economic indicators, and the GIS (Geographic Information System) software. This tool has been tested as part of a CASDAR "Post-MAET Gimone" (agriculture.gouv.fr/ministere/mobilisation-collective-pour-lagroecologie.) project on the subject of "Collective mobilization for agroecology" by using farm data, most of the farms having been involved in an agro-environmental measure for the progressive reduction of phytosanitary treatments since 2008. It has made it possible to compare the agroecological performances of these farms with an optimal situation, as well as with each other. Considering the research objectives and the approaches discussed, this study is an original step in the development of agricultural management strategies in favor of agroecology.

Ecological intensification is a new concept in agriculture that addresses the double challenge of maintaining a level of production sufficient to support needs of human populations and respecting the environment in order to conserve the natural world and human quality of life. This article adapts this concept to fish farming using agroecological principles and the ecosystem services framework. The method was developed from the study of published literature and applications at four study sites chosen for their differences in production intensity: polyculture ponds in France, integrated pig and pond polyculture in Brazil, the culture of striped catfish in Indonesia and a recirculating salmon aquaculture system in France. The study of stakeholders' perceptions of ecosystem services combined with environmental assessment through Life Cycle Assessment and Emergy accounting allowed development of an assessment tool that was used as a basis for co-building evolution scenarios. From this experience, ecological intensification of aquaculture was defined as the use of ecological processes and functions to increase productivity, strengthen ecosystem services and decrease disservices. It is based on aquaecosystem and biodiversity management and the use of local and traditional knowledge. Expected consequences for farming systems consist of greater autonomy, efficiency and better integration into their surrounding territories. Ecological intensification requires territorial governance and helps improve it from a sustainable development perspective.

The fine classification of crops is critical for food security and agricultural management. There are many different species of crops, some of which have similar spectral curves. As a result, the precise classification of crops is a difficult task. Although the classification methods that incorporate spatial information can reduce the noise and improve the classification accuracy, to a certain extent, the problem is far from solved. Therefore, in this paper, the method of spatial–spectral fusion based on conditional random fields (SSF-CRF) for the fine classification of crops in UAV-borne hyperspectral remote sensing imagery is presented. The proposed method designs suitable potential functions in a pairwise conditional random field model, fusing the spectral and spatial features to reduce the spectral variation within the homogenous regions and accurately identify the crops. The experiments on hyperspectral datasets of the cities of Hanchuan and Honghu in China showed that, compared with the traditional methods, the proposed classification method can effectively improve the classification accuracy, protect the edges and shapes of the features, and relieve excessive smoothing, while retaining detailed information. This method has important significance for the fine classification of crops in hyperspectral remote sensing imagery.

The species richness and biodiversity of vegetation in Hungary are increasingly threatened by invasive plant species brought in from other continents and foreign ecosystems. These invasive plant species have spread aggressively in the natural and semi-natural habitats of Europe. Common milkweed (Asclepias syriaca) is one of the species that pose the greatest ecological menace. Therefore, the primary purpose of the present study is to map and monitor the spread of common milkweed, the most common invasive plant species in Europe. Furthermore, the possibilities to detect and validate this special invasive plant by analyzing hyperspectral remote sensing data were investigated. In combination with field reference data, high-resolution hyperspectral aerial images acquired by an unmanned aerial vehicle (UAV) platform in 138 spectral bands in areas infected by common milkweed were examined. Then, support vector machine (SVM) and artificial neural network (ANN) classification algorithms were applied to the highly accurate field reference data. As a result, common milkweed individuals were distinguished in hyperspectral images, achieving an overall accuracy of 92.95% in the case of supervised SVM classification. Using the ANN model, an overall accuracy of 99.61% was achieved. To evaluate the proposed approach, two experimental tests were conducted, and in both cases, we managed to distinguish the individual specimens within the large variety of spreading invasive species in a study area of 2 ha, based on centimeter spatial resolution hyperspectral UAV imagery.

Deep convolutional neural networks have promoted significant progress in building extraction from high-resolution remote sensing imagery. Although most of such work focuses on modifying existing image segmentation networks in computer vision, we propose a new network in this paper, Deep Encoding Network (DE-Net), that is designed for the very problem based on many lately introduced techniques in image segmentation. Four modules are used to construct DE-Net: the inceptionstyle downsampling modules combining a striding convolution layer and a max-pooling layer, the encoding modules comprising six linear residual blocks with a scaled exponential linear unit (SELU) activation function, the compressing modules reducing the feature channels, and a densely upsampling module that enables the network to encode spatial information inside feature maps. Thus, DE-Net achieves stateoftheart performance on the WHU Building Dataset in recall, F1-Score, and intersection over union (IoU) metrics without pretraining. It also outperformed several segmentation networks in our self-built Suzhou Satellite Building Dataset. The experimental results validate the effectiveness of DE-Net on building extraction from aerial imagery and satellite imagery. It also suggests that given enough training data, designing and training a network from scratch may excel fine-tuning models pre-trained on datasets unrelated to building extraction.

Livestock farming is criticized for negatively impacting the environment, concerns about animal welfare and the impact of excessive meat consumption on human health. However, livestock farming provides other underappreciated and poorly communicated benefits to society in terms of employment, product quality, cultural landscapes and carbon storage by grasslands. Few attempts have been made so far to simultaneously consider the services and impacts provided by livestock production. Here, we propose an integrated graphical tool, called the 'barn' to explicitly summarize the synergies and trade-offs between services and impacts provided by livestock farming. It illustrates livestock farming interacting with its physical, economic and social environment along five interfaces: (i) Markets, (ii) Work and employment, (iii) Inputs, (iv) Environment and climate, (v) Social and cultural factors. This graphical tool was then applied by comparing two contrasting livestock production areas (high livestock density v. grassland-based), and the dominant v. a niche system within a crop-livestock area. We showed the barn could be used for cross-comparisons of services and impacts across livestock production areas, and for multi-level analysis of services and impacts of livestock farming within a given area. The barn graphically summarizes the ecological and socio-economic aspects of livestock farming by explicitly representing multiple services and impacts of different systems in a simple yet informative way. Information for the five interfaces relies on available quantitative assessments from the literature or data sets, and on expert-knowledge for more qualitative factors, such as social and cultural ones. The 'barn' can also inform local stakeholders or policy-makers about potential opportunities and threats to the future of livestock farming in specific production areas. It has already been used as a pedagogical tool for teaching the diversity of services and impacts of livestock systems across Europe and is currently developed as a serious game for encouraging knowledge exchange and sharing different viewpoints between stakeholders.

Evaluating agricultural ecology can help us to understand regional environmental status and contribute to the sustainable development of agricultural ecosystems. Furthermore, the results of eco-environmental assessment can provide data support for policy-making and agricultural production. The application of multi-source remote-sensing technology has the advantages of being fast, accurate and wide ranging. It can reveal the status of regional ecological environments, and is of great significance to monitoring their quality. In this paper, an agroecological efficiency evaluation model was constructed by combining remote sensing data and ecological index (EI). Multi-source remote-sensing data were used to obtain the evaluation index. Indicators collected from satellites, such as biological richness, vegetation cover, water network density, land stress, and pollution load, were used to quantitatively evaluate the agroecological efficiency of Rangtang County in the Tibetan Plateau. The results showed that the EI of Rangtang County increased from 61.77 to 65.10 during 2000–2020, which means that the eco-environmental quality of this area was good, and it has shown an obviously improving trend over the past 20 years. Rangtang County has converted more than 30 km²of grassland into woodland over the past 20 years. Climate change and human activities have had combined effects on the ecological environment of this area. The change in ecological environment quality is greatly affected by human disturbance. Policymakers should continue setting up nature reserves and should implement the policy of returning farmland to forests. Unreasonable grazing and rational allocation of land resources are still critical points of concern for future ecological environment construction. EI, combined with remote sensing and statistical data, is proven to be able to reasonably represent changes in ecological environment in Rangtang County, thus providing more possibilities for ecological evaluation on the Tibetan Plateau, and even the whole world.

. Land cover (LC) determines the energy exchange, water and carbon cycle between Earth's spheres. Accurate LC information is a fundamental parameter for the environment and climate studies. Considering that the LC in China has been altered dramatically with the economic development in the past few decades, sequential and fine-scale LC monitoring is in urgent need. However, currently, fine-resolution annual LC dataset produced by the observational images is generally unavailable for China due to the lack of sufficient training samples and computational capabilities. To deal with this issue, we produced the first Landsat-derived annual China land cover dataset (CLCD) on the Google Earth Engine (GEE) platform, which contains 30 m annual LC and its dynamics in China from 1990 to 2019. We first collected the training samples by combining stable samples extracted from China's land-use/cover datasets (CLUDs) and visually interpreted samples from satellite time-series data, Google Earth and Google Maps. Using 335 709 Landsat images on the GEE, several temporal metrics were constructed and fed to the random forest classifier to obtain classification results. We then proposed a post-processing method incorporating spatial–temporal filtering and logical reasoning to further improve the spatial–temporal consistency of CLCD. Finally, the overall accuracy of CLCD reached 79.31 % based on 5463 visually interpreted samples. A further assessment based on 5131 third-party test samples showed that the overall accuracy of CLCD outperforms that of MCD12Q1, ESACCI_LC, FROM_GLC and GlobeLand30. Besides, we intercompared the CLCD with several Landsat-derived thematic products, which exhibited good consistencies with the Global Forest Change, the Global Surface Water, and three impervious surface products. Based on the CLCD, the trends and patterns of China's LC changes during 1985 and 2019 were revealed, such as expansion of impervious surface (+148.71 %) and water (+18.39 %), decrease in cropland (−4.85 %) and grassland (−3.29 %), and increase in forest (+4.34 %). In general, CLCD reflected the rapid urbanization and a series of ecological projects (e.g. Gain for Green) in China and revealed the anthropogenic implications on LC under the condition of climate change, signifying its potential application in the global change research. The CLCD dataset introduced in this article is freely available at https://doi.org/10.5281/zenodo.4417810 (Yang and Huang, 2021).

. The amount of impervious surface is an important\nindicator in the monitoring of the intensity of human activity and\nenvironmental change. The use of remote sensing techniques is the only means\nof accurately carrying out global mapping of impervious surfaces covering\nlarge areas. Optical imagery can capture surface reflectance\ncharacteristics, while synthetic-aperture radar (SAR) images can be used to\nprovide information on the structure and dielectric properties of surface\nmaterials. In addition, nighttime light (NTL) imagery can detect the\nintensity of human activity and thus provide important a priori\nprobabilities of the occurrence of impervious surfaces. In this study, we\naimed to generate an accurate global impervious surface map at a resolution\nof 30 m for 2015 by combining Landsat 8 Operational Land Image (OLI) optical images, Sentinel-1 SAR\nimages and Visible Infrared Imaging Radiometer Suite (VIIRS) NTL images based on\nthe Google Earth Engine (GEE) platform. First, the global impervious and\nnonimpervious training samples were automatically derived by combining the\nGlobeLand30 land-cover product with VIIRS NTL and MODIS enhanced vegetation\nindex (EVI) imagery. Then, the local adaptive random forest classifiers,\nallowing for a regional adjustment of the classification parameters to take into\naccount the regional characteristics, were trained and used to generate\nregional impervious surface maps for each 5∘×5∘ geographical grid using local training samples and multisource\nand multitemporal imagery. Finally, a global impervious surface map,\nproduced by mosaicking numerous 5∘×5∘\nregional maps, was validated by interpretation samples and then compared\nwith five existing impervious products (GlobeLand30, FROM-GLC, NUACI, HBASE and GHSL). The results indicated that the global\nimpervious surface map produced using the proposed multisource,\nmultitemporal random forest classification (MSMT_RF) method\nwas the most accurate of the maps, having an overall accuracy of 95.1 %\nand kappa coefficient (one of the most commonly used statistics to test\ninterrater reliability; Olofsson et al., 2014) of 0.898 as\nagainst 85.6 % and 0.695 for NUACI, 89.6 % and 0.780 for\nFROM-GLC, 90.3 % and 0.794 for GHSL, 88.4 % and 0.753 for\nGlobeLand30, and 88.0 % and 0.745 for HBASE using all 15 regional\nvalidation data. Therefore, it is concluded that a global 30 m impervious\nsurface map can accurately and efficiently be generated by the proposed\nMSMT_RF method based on the GEE platform. The global\nimpervious surface map generated in this paper is available at https://doi.org/10.5281/zenodo.3505079 (Zhang and Liu, 2019).\n

Unlike satellite images, which are typically acquired and processed in near-real-time, global land cover products have historically been produced on an annual basis, often with substantial lag times between image processing and dataset release. We developed a new automated approach for globally consistent, high resolution, near real-time (NRT) land use land cover (LULC) classification leveraging deep learning on 10 m Sentinel-2 imagery. We utilize a highly scalable cloud-based system to apply this approach and provide an open, continuous feed of LULC predictions in parallel with Sentinel-2 acquisitions. This first-of-its-kind NRT product, which we collectively refer to as Dynamic World, accommodates a variety of user needs ranging from extremely up-to-date LULC data to custom global composites representing user-specified date ranges. Furthermore, the continuous nature of the product’s outputs enables refinement, extension, and even redefinition of the LULC classification. In combination, these unique attributes enable unprecedented flexibility for a diverse community of users across a variety of disciplines.

建筑物图斑变化检测是遥感影像信息提取的重要内容之一,对于土地调查、自然资源常态化监测、土地执法监测等具有重要意义。岭南地区建设结构复杂,高分辨率遥感影像信息丰富,包含建筑结构细节多种多样,加上成像的季节不同、时间不同等因素导致建筑物变化信息的自动提取十分困难。针对此问题,本文提出了基于HRNet的语义分割模型,通过筛选保留高分辨率的特征层,从而保留更细节的图像信息。此外,结合图像分割二值化对结果进行优化,在一定程度上提高了高分辨率遥感影像建筑物变化自动检测的能力。

Building change extraction is one of the important research areas of remote sensing image information extraction, which is of great significance for land survey, natural resources monitoring and land law enforcement. The complex construction structure in Lingnan area of China contains a variety of building structure details, which reflect rich information on the high-resolution remote sensing images, and the factors of influence such as abundant data sources and imaging seasonal differences. It makes the automatic extraction of building change information very difficult. To address this problem, this paper proposes a semantic segmentation model based on HRNet, which achieves the retention of more detailed texture information by screening the feature layers that retain high resolution. On this basis, the automatic detection capability of building changes in high-resolution remote sensing images is improved by GraphCut binarization optimization.

针对利用传统卷积神经网络进行路面裂缝分割时存在准确率低、信息丢失及边缘模糊的问题,本文提出了基于改进HRNet模型的路面裂缝分割算法。模型在原始HRNet的基础上进行改进,主干网络部分采用DUC模块代替双线性插值上采样;下采样改为passthrough layer代替原始卷积;在模型解码部分,进行逐级上采样的同时引入SE-Block,对不同特征层的融合重新标定权重。通过与原始HRNet及传统卷积神经网络U-Net对比可知,本文算法在公共数据与自制数据集上的分割精度表现优秀,F1分值分别达到了91.31%和78.69%,可以很好地满足实际工程的需求。

Aiming at the problems of low accuracy,loss of information and blurred edges in the traditional convolutional neural network for pavement crack segmentation,a pavement crack segmentation algorithm based on the improved HRNet model is proposed.The model is improved on the basis of the original HRNet,the backbone network part uses DUC module instead of bilinear interpolation;downsampling is changed to passthrough layer to replace the original convolution,SE-Block is introduced while performing step-by-step upsampling to re-calibrate the fusion of different feature layers.Comparing with the original HRNet and the other traditional convolutional neural networks U-Net,it can be concluded that the segmentation accuracy of this algorithm is the best on public data and self-made data sets,with <i>F1</i> score reaching 91.31% and 78.69% respectively,proving that the algorithm can be very good to meet the needs of actual engineering.