1
|
Gao M, Lu T, Wang L. Crop Mapping Based on Sentinel-2 Images Using Semantic Segmentation Model of Attention Mechanism. SENSORS (BASEL, SWITZERLAND) 2023; 23:7008. [PMID: 37571791 PMCID: PMC10422268 DOI: 10.3390/s23157008] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/28/2023] [Revised: 08/02/2023] [Accepted: 08/04/2023] [Indexed: 08/13/2023]
Abstract
Using remote sensing images to identify crop plots and estimate crop planting area is an important part of agricultural remote sensing monitoring. High-resolution remote sensing images can provide rich information regarding texture, tone, shape, and spectrum of ground objects. With the advancement of sensor and information technologies, it is now possible to categorize crops with pinpoint accuracy. This study defines crop mapping as a semantic segmentation problem; therefore, a deep learning method is proposed to identify the distribution of corn and soybean using the differences in the spatial and spectral features of crops. The study area is located in the southwest of the Great Lakes in the United States, where corn and soybean cultivation is concentrated. The proposed attention mechanism deep learning model, A2SegNet, was trained and evaluated using three years of Sentinel-2 data, collected between 2019 and 2021. The experimental results show that this method is able to fully extract the spatial and spectral characteristics of crops, and its classification effect is significantly better than that of the baseline method, and it has better classification performance than other deep learning models. We cross verified the trained model on the test sets of different years through transfer learning in both spatiotemporal and spatial dimensions. Proving the effectiveness of the attention mechanism in the process of knowledge transfer, A2SegNet showed better adaptability.
Collapse
Affiliation(s)
- Meixiang Gao
- Department of Geography and Spatial Information Techniques, Ningbo University, Ningbo 315211, China;
| | - Tingyu Lu
- College of Geography and Environmental Sciences, Hainan Normal University, Haikou 571158, China
| | - Lei Wang
- Heilongjiang Province Key Laboratory of Geographical Environment Monitoring and Spatial Information Service in Cold Regions, Harbin Normal University, Harbin 150025, China;
| |
Collapse
|
2
|
Water, energy and climate benefits of urban greening throughout Europe under different climatic scenarios. Sci Rep 2021; 11:12163. [PMID: 34108503 PMCID: PMC8190137 DOI: 10.1038/s41598-021-88141-7] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2020] [Accepted: 03/08/2021] [Indexed: 11/11/2022] Open
Abstract
Urban greening is an effective mitigation option for climate change in urban areas. In this contribution, a European Union (EU)-wide assessment is presented to quantify the benefits of urban greening in terms of availability of green water, reduction of cooling costs and CO2 sequestration from the atmosphere, for different climatic scenarios. Results show that greening of 35% of the EU’s urban surface (i.e. more than 26,000 km2) would avoid up to 55.8 Mtons year−1 CO2 equivalent of greenhouse gas emissions, reducing energy demand for the cooling of buildings in summer by up to 92 TWh per year, with a net present value (NPV) of more than 364 billion Euro. It would also transpire about 10 km3 year−1 of rain water, turning into “green” water about 17.5% of the “blue” water that is now urban runoff, helping reduce pollution of the receiving water bodies and urban flooding. The greening of urban surfaces would decrease their summer temperature by 2.5–6 °C, with a mitigation of the urban heat island effect estimated to have a NPV of 221 billion Euro over a period of 40 years. The monetized benefits cover less than half of the estimated costs of greening, having a NPV of 1323 billion Euro on the same period. Net of the monetized benefits, the cost of greening 26,000 km2 of urban surfaces in Europe is estimated around 60 Euro year−1 per European urban resident. The additional benefits of urban greening related to biodiversity, water quality, health, wellbeing and other aspects, although not monetized in this study, might be worth such extra cost. When this is the case, urban greening represents a multifunctional, no-regret, cost-effective solution.
Collapse
|
3
|
Quaranta E, Dorati C, Pistocchi A. Meta-models for rapid appraisal of the benefits of urban greening in the European context. JOURNAL OF HYDROLOGY. REGIONAL STUDIES 2021; 34:100772. [PMID: 33821201 PMCID: PMC8008813 DOI: 10.1016/j.ejrh.2021.100772] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/24/2020] [Revised: 12/27/2020] [Accepted: 12/29/2020] [Indexed: 06/12/2023]
Abstract
STUDY REGION This study considers daily time series of 14 years of weather parameters (temperature, wind speed, rainfall, vapor pressure and radiation) for 671 functional urban areas (FUA) across Europe, from a latitude of 35° (Cyprus) to 65° (Finland). STUDY FOCUS Quantification of urban greening effects usually requires relatively complex and integrated models. In this contribution, we apply well-established hydrological, biomass and energy balance equations to derive meta-models for the estimation of runoff reduction, urban surface heating and thermal protection of buildings, in order to quantify the effects of the greening of 1 m2 of impervious surface (e.g. roofs, sealed ground surfaces and underground parking lots). NEW HYDROLOGICAL INSIGHTS FOR THE REGION We propose empirical meta-models for the quick appraisal of urban greening benefits including: urban runoff reduction due to soil water retention and evapotranspiration, land surface temperature reduction, reduction of the indoor temperature beneath the greened surface, dry biomass growth. We show that the choice of vegetation growth parameters has a limited effect on the results, although the amount of produced bulk biomass obviously depends on vegetation type. The proposed meta-models can be applied for the assessment of urban greening benefits at the stage of policy evaluation, land planning and the programming of investments at regional or continental scale, before undertaking more detailed and site-specific calculations as required in the design phase.
Collapse
Affiliation(s)
| | - Chiara Dorati
- ARHS Italia www.arhs-group.com, External Consultant for the European Commission, Italy
| | | |
Collapse
|
4
|
Yang X, Tan M. Attributing Global Land Carbon Loss to Regional Agricultural and Forestry Commodity Consumption. ENVIRONMENTAL SCIENCE & TECHNOLOGY 2021; 55:823-831. [PMID: 33382577 DOI: 10.1021/acs.est.0c04222] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
One of the critical components in climate change mitigation lies in meeting the challenge of reducing global land carbon loss, as human demand increases. Yet, it is unclear which region and which form of commodity consumption were responsible for the greatest loss of land carbon. Here we assumed a uniform lifespan (20-year) for managed land and took the managed land in 2010 as a reference to estimate the land carbon loss for region-commodity on a global scale. The estimates and multi-region input-output table were then combined to identify the regions and commodities that contributed the most to global land carbon loss from the consumption side. The results show that during the lifespan, global consumption for agricultural and forestry commodities excluding wood fuel lost a total of 15.6 Pg in land carbon annually, of which 29% and 25% were attributed to beef and wood consumption, respectively. Land carbon loss per capita consumption was highest in high-income regions (Australia, the United States, Canada, Japan, and Europe) primarily due to the high consumed quantity for commodities per capita in these areas. Further, the net importers for land carbon were usually high-income regions (they held lower land carbon loss per unit of production), which was not conducive to reducing global land carbon loss. The research could contribute to discussions of climate responsibility and then inform climate mitigation policies.
Collapse
Affiliation(s)
- Xue Yang
- Energy Studies Institute, National University of Singapore, Singapore 119620, Singapore
| | - Minghong Tan
- Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
| |
Collapse
|
5
|
Janes-Bassett V, Davies J, Rowe EC, Tipping E. Simulating long-term carbon nitrogen and phosphorus biogeochemical cycling in agricultural environments. THE SCIENCE OF THE TOTAL ENVIRONMENT 2020; 714:136599. [PMID: 31982737 DOI: 10.1016/j.scitotenv.2020.136599] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/06/2019] [Revised: 01/07/2020] [Accepted: 01/07/2020] [Indexed: 05/25/2023]
Abstract
Understanding how agricultural practices alter biogeochemical cycles is vital for maintaining land productivity, food security, and other ecosystem services such as carbon sequestration. However, these are complex, highly coupled long-term processes that are difficult to observe or explore through empirical science alone. Models are required that capture the main anthropogenic disturbances, whilst operating across regions and long timescales, simulating both natural and agricultural environments, and shifts among these. Many biogeochemical models neglect agriculture or interactions between carbon and nutrient cycles, which is surprising given the scale of intervention in nitrogen and phosphorus cycles introduced by agriculture. This gap is addressed here, using a plant-soil model that simulates integrated soil carbon, nitrogen and phosphorus (CNP) cycling across natural, semi-natural and agricultural environments. The model is rigorously tested both spatially and temporally using data from long-term agricultural experiments across temperate environments. The model proved capable of reproducing the magnitude of and trends in soil nutrient stocks, and yield responses to nutrient addition. The model has potential to simulate anthropogenic effects on biogeochemical cycles across northern Europe, for long timescales (centuries) without site-specific calibration, using easily accessible input data. The results demonstrate that weatherable P from parent material has a considerable effect on modern pools of soil C and N, despite significant perturbation of nutrient cycling from agricultural practices, highlighting the need to integrate both geological and agricultural processes to understand effects of land-use change on food security, C storage and nutrient sustainability. The results suggest that an important process or source of P is currently missing in our understanding of agricultural biogeochemical cycles. The model could not explain how yields were sustained in plots with low P fertiliser addition. We suggest that plant access to organic P is a key uncertainty warranting further research, particularly given sustainability concerns surrounding rock sources of P fertiliser.
Collapse
Affiliation(s)
- Victoria Janes-Bassett
- Pentland Centre for Sustainability in Business, Lancaster Environment Centre, Lancaster University, UK.
| | - Jessica Davies
- Pentland Centre for Sustainability in Business, Lancaster Environment Centre, Lancaster University, UK
| | - Ed C Rowe
- Centre for Ecology and Hydrology, Bangor, UK
| | | |
Collapse
|
6
|
Spawn SA, Sullivan CC, Lark TJ, Gibbs HK. Harmonized global maps of above and belowground biomass carbon density in the year 2010. Sci Data 2020; 7:112. [PMID: 32249772 PMCID: PMC7136222 DOI: 10.1038/s41597-020-0444-4] [Citation(s) in RCA: 62] [Impact Index Per Article: 15.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2019] [Accepted: 02/14/2020] [Indexed: 11/09/2022] Open
Abstract
Remotely sensed biomass carbon density maps are widely used for myriad scientific and policy applications, but all remain limited in scope. They often only represent a single vegetation type and rarely account for carbon stocks in belowground biomass. To date, no global product integrates these disparate estimates into an all-encompassing map at a scale appropriate for many modelling or decision-making applications. We developed an approach for harmonizing vegetation-specific maps of both above and belowground biomass into a single, comprehensive representation of each. We overlaid input maps and allocated their estimates in proportion to the relative spatial extent of each vegetation type using ancillary maps of percent tree cover and landcover, and a rule-based decision schema. The resulting maps consistently and seamlessly report biomass carbon density estimates across a wide range of vegetation types in 2010 with quantified uncertainty. They do so for the globe at an unprecedented 300-meter spatial resolution and can be used to more holistically account for diverse vegetation carbon stocks in global analyses and greenhouse gas inventories.
Collapse
Affiliation(s)
- Seth A Spawn
- Department of Geography, University of Wisconsin-Madison, Madison, WI, USA.
- Center for Sustainability and the Global Environment (SAGE), Nelson Institute for Environmental Studies, University of Wisconsin-Madison, Madison, WI, USA.
| | - Clare C Sullivan
- Department of Geography, University of Wisconsin-Madison, Madison, WI, USA
- Center for Sustainability and the Global Environment (SAGE), Nelson Institute for Environmental Studies, University of Wisconsin-Madison, Madison, WI, USA
| | - Tyler J Lark
- Center for Sustainability and the Global Environment (SAGE), Nelson Institute for Environmental Studies, University of Wisconsin-Madison, Madison, WI, USA
| | - Holly K Gibbs
- Department of Geography, University of Wisconsin-Madison, Madison, WI, USA
- Center for Sustainability and the Global Environment (SAGE), Nelson Institute for Environmental Studies, University of Wisconsin-Madison, Madison, WI, USA
| |
Collapse
|
7
|
Ma J, Xiao X, Zhang Y, Doughty R, Chen B, Zhao B. Spatial-temporal consistency between gross primary productivity and solar-induced chlorophyll fluorescence of vegetation in China during 2007-2014. THE SCIENCE OF THE TOTAL ENVIRONMENT 2018; 639:1241-1253. [PMID: 29929291 DOI: 10.1016/j.scitotenv.2018.05.245] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/13/2017] [Revised: 05/11/2018] [Accepted: 05/20/2018] [Indexed: 06/08/2023]
Abstract
Accurately estimating spatial-temporal patterns of gross primary production (GPP) is important for the global carbon cycle. Satellite-based light use efficiency (LUE) models are regarded as an efficient tool in simulating spatial-temporal dynamics of GPP. However, the accuracy assessment of GPP simulations from LUE models at both spatial and temporal scales remains a challenge. In this study, we simulated GPP of vegetation in China during 2007-2014 using a LUE model (Vegetation Photosynthesis Model, VPM) based on MODIS (moderate-resolution imaging spectroradiometer) images with 8-day temporal and 500-m spatial resolutions and NCEP (National Center for Environmental Prediction) climate data. Global Ozone Monitoring Instrument 2 (GOME-2) solar-induced chlorophyll fluorescence (SIF) data were used to compare with VPM simulated GPP (GPPVPM) temporally and spatially using linear correlation analysis. Significant positive linear correlations exist between monthly GPPVPM and SIF data over a single year (2010) and multiple years (2007-2014) in most areas of China. GPPVPM is also significantly positive correlated with GOME-2 SIF (R2 > 0.43) spatially for seasonal scales. However, poor consistency was detected between GPPVPM and SIF data at yearly scale. GPP dynamic trends have high spatial-temporal variation in China during 2007-2014. Temperature, leaf area index (LAI), and precipitation are the most important factors influence GPPVPM in the regions of East Qinghai-Tibet Plateau, Loss Plateau, and Southwestern China, respectively. The results of this study indicate that GPPVPM is temporally and spatially in line with GOME-2 SIF data, and space-borne SIF data have great potential for evaluating LUE-based GPP models.
Collapse
Affiliation(s)
- Jun Ma
- Ministry of Education Key Laboratory for Biodiversity Science and Ecological Engineering, Shanghai Chongming Dongtan Wetland Ecosystem Research Station, Shanghai Institute of Eco-Chongming (SIEC), Fudan University, Shanghai 200433, China
| | - Xiangming Xiao
- Ministry of Education Key Laboratory for Biodiversity Science and Ecological Engineering, Shanghai Chongming Dongtan Wetland Ecosystem Research Station, Shanghai Institute of Eco-Chongming (SIEC), Fudan University, Shanghai 200433, China; Department of Microbiology and Plant Biology, Center for Spatial Analysis, University of Oklahoma, Norman, OK 73019, USA.
| | - Yao Zhang
- Department of Microbiology and Plant Biology, Center for Spatial Analysis, University of Oklahoma, Norman, OK 73019, USA
| | - Russell Doughty
- Department of Microbiology and Plant Biology, Center for Spatial Analysis, University of Oklahoma, Norman, OK 73019, USA
| | - Bangqian Chen
- Danzhou Investigation & Experiment Station of Tropical Cops, Ministry of Agriculture, Rubber Research Institute, Chinese Academy of Tropical Agricultural Sciences (CATAS), Danzhou 571737, China
| | - Bin Zhao
- Ministry of Education Key Laboratory for Biodiversity Science and Ecological Engineering, Shanghai Chongming Dongtan Wetland Ecosystem Research Station, Shanghai Institute of Eco-Chongming (SIEC), Fudan University, Shanghai 200433, China
| |
Collapse
|
8
|
Li Z, Liu S, Tan Z, Sohl TL, Wu Y. Simulating the effects of management practices on cropland soil organic carbon changes in the Temperate Prairies Ecoregion of the United States from 1980 to 2012. Ecol Modell 2017. [DOI: 10.1016/j.ecolmodel.2017.09.017] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
9
|
Modeling terrestrial ecosystem productivity of an estuarine ecosystem in the Sundarban Biosphere Region, India using seven ecosystem models. Ecol Modell 2017. [DOI: 10.1016/j.ecolmodel.2017.03.003] [Citation(s) in RCA: 17] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022]
|
10
|
Li Z, Liu S, Zhang X, West TO, Ogle SM, Zhou N. Evaluating land cover influences on model uncertainties—A case study of cropland carbon dynamics in the Mid-Continent Intensive Campaign region. Ecol Modell 2016. [DOI: 10.1016/j.ecolmodel.2016.07.002] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
11
|
Yu B, Chen F. The global impact factors of net primary production in different land cover types from 2005 to 2011. SPRINGERPLUS 2016; 5:1235. [PMID: 27536518 PMCID: PMC4971002 DOI: 10.1186/s40064-016-2910-1] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/18/2016] [Accepted: 07/25/2016] [Indexed: 11/10/2022]
Abstract
With the seriously polluted environment due to social development, the sustainability of net primary production (NPP), which is used to feed most lives on the earth, has become one of the biggest concerns that we have to consider for the sake of food shortage. There have been many researches analyzing one or two potential impact factors of NPP based on field observation data, which brings about many uncertainties for further calculation. Moreover, the frequently used process-based models heavily depend on the understandings of researchers about the NPP process. The premises of such models hinder the impact factor analysis from being objective and confident. To overcome such shortages, we collected 27 potential impact factors of global NPP in terms of eight land cover types. The feature variables include atmosphere, biosphere, anthroposphere and lithosphere parameters, which can be obtained from public available remote sensed products. The experiment shows that latitude, irradiance ultraviolet and normalized difference vegetation index are dominant factors impacting global NPP. Anthropogenic activities, precipitation and surface emissivity are influencing NPP calculation largely. However, some commonly used biosphere parameters in process-based models are actually not playing that important roles in NPP estimation. This work provides a new insight in analyzing NPP impact factors, being more objective and comprehensive compared with frequently used process-based models.
Collapse
Affiliation(s)
- Bo Yu
- Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing, 100101 China
| | - Fang Chen
- Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing, 100101 China ; Hainan Key Laboratory of Earth Observation, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Sanya, 572029 China
| |
Collapse
|
12
|
Assessing the Impact of Climate Variability on Cropland Productivity in the Canadian Prairies Using Time Series MODIS FAPAR. REMOTE SENSING 2016. [DOI: 10.3390/rs8040281] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/03/2023]
|