Cropland Extent Research Articles

“Cropland characteristics and extent of soil loss by rill and gully erosion in smallholder farms in the KIVU highlands, D.R. Congo”

Soil erosion is a widespread phenomenon threatening the sustainability of agricultural production in the South-Kivu highlands (eastern D.R. Congo), as is the case in other cultivated areas of the East-African highlands. However, quantitative estimates of soil erosion on farm are scarce. To address this, the extent of erosion and associated explanatory factors were studied in two representative watersheds across a wide range of cropping systems and soil characteristics. Rill and gully erosion volumes were measured every 2 weeks in 90 fields by the transect methods during four successive long (SA) and short (SB) rainy seasons (2015–2017). Additionally, field characteristics and rainfall were collected. Results show that the average soil loss rate was significantly different between seasons, with rates of 3.1 and 1.9 mm in season A-2015, 1.8 and 2.7 mm in season B-2016, 2.2 and 3.3 mm in season A-2016 and 3.2 and 3.8 mm in Season B-2017 for minimum rill (damage area) and gully erosion (whole field), respectively. As a result of differences both in natural factors (e.g., precipitation and slope steepness) and management conditions (cropping systems and soil cover) across farmers' fields, there was a large variability in cumulative soil erosion rates across fields, from 0.03 to 18 mm for minimum rill erosion and from 0.13 to 11.7 mm for gully erosion rates over the 4 seasons. For 41% of fields, rill erosion rates are higher than the tolerable soil loss generally set at 12.5 t/ha/year (or 1 mm/year) for the most fertile soils. Low minimum rill erosion rates tended to be associated with high pH, sum of bases and effective CEC, while high erosion rates were associated with high topsoil depth in both watersheds. Cassava-based cropping systems tended to be associated with high rill erosion rates, while higher rainfall increased both rill and gully erosion rates. Overall, the very high measured rill erosion rates suggest the urgent need for implementation of erosion control strategies. The results could be used to prioritize sites at risk of water erosion at the small watershed scale in order to install mitigation measures.

Crop harvested area, not yield, drives variability in crop production in Iran

Increasing population and a severe water crisis are imposing growing pressure on Iranian cropping systems to increase crop production to meet the rising demand for food. Little is known about the separate contribution of trends and variability of the harvested area and yield to crop production in severely drought-prone areas such as Iran. In this study we (a) quantify the importance of harvested area and yield on trends and variability of crop production for the 12 most important annual crops under rainfed and irrigated conditions and (b) test how well the variability in annual crop areas can be explained by drought dynamics. We use remote sensing based land cover and evapotranspiration products derived from the Moderate Resolution Imaging Spectroradiometer to quantify the extent of cropland and drought severity as well as survey-based, crop-specific reports for the period 2001–2016 in Iran. The intensity of drought stress was estimated using the annual ratio between actual and potential evapotranspiration. We found that trends in the production of specific crops are predominantly explained by trends in harvested crop area. Besides, the variability in the harvested area contributed significantly more to the variability in crop production than the variability in crop yields, particularly under rainfed conditions (seven out of nine crops). In contrast, variability in the production of heavily subsidized crops such as wheat was predominantly explained by yield variability. Variability in the annual cropland area was largely explained by drought, in particular for the more arid regions in the south of the country. This highlights the importance of better and proactive drought management to stabilize crop areas and yields for sufficient food production in Iran.

Global patterns and potential drivers of human settlements within protected areas

Protected areas (PAs) represent one of our most important conservation strategies for halting biodiversity loss. The number of PAs has increased remarkably over the last few decades. Yet, biodiversity is still being lost at alarming rates, even within many of those PAs. Understanding the factors that influence the levels of human pressure within PAs remains a key objective. In this study, we examined the factors associated with the human settlements’ levels within the world’s PAs. Using the random forests technique, an ensemble machine learning method, and a vast number of PAs (81 100–137 523), we assessed the importance of nine factors, including the PAs’ management objective as reflected by their International Union for Conservation of Nature (IUCN) Category. The IUCN classifies PAs into six categories ranging from strict nature reserves to areas in which multiple human uses are permitted. The prevalent but untested assumption is that human settlements’ levels within PAs vary according to their management objective, with less strict PAs having higher levels. Our results, however, show that the differences between the categories were for the most part minor. The most important predictor of human settlements was accessibility measured as the time required to reach the PA from the nearest major city. These findings were consistent across all of the world’s subregions. Other less important factors included the extent of croplands within PAs, elevation, and slope. Our findings suggest that PAs nearer urban centers tend to have higher human settlements’ levels regardless of their other characteristics, such as management objective and year of establishment. Managing those PAs successfully will be necessary to achieve the post-2020 global biodiversity targets and will require conservation strategies that acknowledge and engage the local communities.

Decadal variability modulates trends in concurrent heat and drought over global croplands

Extreme heat and drought often reduce the yields of important food crops around the world, putting stress on regional and global food security. The probability of concurrently hot and dry conditions, which can have compounding impacts on crops, has already increased in many regions of the globe. The evolution of these trends in coming decades could have important impacts on global food security. However, regional variation and the influence of natural climate variability on these trends remains an important gap in understanding future climate risk to crops. In this study, we examine trends in concurrent hot-and-dry extremes over global maize and wheat croplands since 1950. We find that the mean extent of cropland in a joint hot-and-dry extreme increased by ∼2% over 1950–2009, and this trend has accelerated substantially since the mid-2000s, notably in the tropics. While joint hot-and-dry seasons affected at most 1%–2% of global cropland per year during the mid-20th century, they regularly exceeded this extent after about 1980, affecting up to 5% of global crop area. These results suggest that the global climate is transitioning from one in which concurrent heat and drought occur rarely to one in which they occur over an important fraction of croplands every year. While these long-term global trends are primarily attributable to anthropogenic climate change, we find they have been suppressed by decadal climate variability in some regions, especially ones with chronic food insecurity. Potential reversals in these tendencies of decadal variability would accelerate exposure of croplands to concurrent heat and drought in coming decades. We conclude by highlighting the need for research and adaptive interventions around multivariate hazards to global crops across timescales.

Climate and Socioeconomic Factors Drive Irrigated Agriculture Dynamics in the Lower Colorado River Basin

The Colorado River Basin (CRB) includes seven states and provides municipal and industrial water to millions of people across all major southwestern cities both inside and outside the basin. Agriculture is the largest part of the CRB economy and crop production depends on irrigation, which accounts for about 74% of the total water demand cross the region. A better understanding of irrigation water demands is critically needed as temperatures continue to rise and drought intensifies, potentially leading to water shortages across the region. Yet, past research on irrigation dynamics has generally utilized relatively low spatiotemporal resolution datasets and has often overlooked the relationship between climate and management decisions such as land fallowing, i.e., the practice of leaving cultivated land idle for a growing season. Here, we produced annual estimates of fallow and active cropland extent at high spatial resolution (30 m) from 2001 to 2017 by applying the fallow-land algorithm based on neighborhood and temporal anomalies (FANTA). We specifically focused on diverse CRB agricultural regions: the lower Colorado River planning (LCRP) area and the Pinal and Phoenix active management areas (PPAMA). Utilizing ground observations collected in 2014 and 2017, we found an overall classification accuracy of 88.9% and 87.2% for LCRP and PPAMA, respectively. We then quantified how factors such as climate, district water rights, and market value influenced: (1) annual fallow and active cropland extent and (2) annual cropland productivity, approximated by integrated growing season NDVI (iNDVI). We found that for the LCRP, a region of winter cropping and senior (i.e., preferential) water rights, active cropland productivity was positively correlated with cool-season average vapor pressure deficit (R = 0.72; p < 0.01). By contrast, for the PPAMA, a region of summer cropping and junior water rights, annual fallow and active cropland extent was positively correlated with cool-season aridity (precipitation/potential evapotranspiration) (R = 0.46; p < 0.05), and active cropland productivity was positively correlated with warm-season aridity (precipitation/potential evapotranspiration) (R = 0.42; p < 0.01). We also found that PPAMA cropland productivity was more sensitive to aridity when crop prices were low, potentially due to the influence of market value on management decisions. Our analysis highlights how biophysical (e.g., temperature and precipitation) and socioeconomic (e.g., water rights and crop market value) factors interact to explain seasonal patterns of cropland extent, water use and productivity. These findings indicate that increasing aridity across the region may result in reduced cropland productivity and increased land fallowing for some regions, particularly those with junior water rights.

Assessing the impacts of watershed interventions using ground data and remote sensing: a case study in Ethiopia

Quantifying the temporal and spatial changes due to watershed interventions is important for assessing the effectiveness of natural resource management practices on vegetative cover and sediment management. This study assessed the performance of natural resource management in a target site (Aba Gerima) and compared the collateral impacts on neighbouring watersheds in Ethiopia in terms of land-use land-cover change. Changes in the extent of cropland, grassland and shrubland were assessed in the target watershed and the non-treated neighbouring watersheds using temporal satellite imagery. In addition, ground monitoring was applied to quantify the impacts on sediment accumulation, fodder biomass and vegetative cover intensity. The study findings showed substantial changes over the study period: mainly, a change from degraded and barren land to restored vegetation in the target watershed, but a continued trend of land-use change from perennial vegetation to cropland in the neighbouring untreated watersheds. There was a decrease in the rate of conversion of vegetative land cover to cropland in the target watershed, and significant on-site changes in sediment retention, fodder productivity and vegetation intensity. The study findings demonstrate a link between management interventions and improvement in soil and vegetation ecosystem functions. These results not only indicate that watershed-level interventions improve on-site soil and water environmental services but also underline the role of community managed land-use regulations in reducing pressure on natural land-use systems and thereby serve the major goal of up-scaling sustainable land management.

Identifying Agricultural Frontiers for Modeling Global Cropland Expansion

SummaryThe increasing expansion of cropland is major driver of global carbon emissions and biodiversity loss. However, predicting plausible future global distributions of croplands remains challenging. Here, we show that, in general, existing global data aligned with classical economic theories of expansion explain the current (1992) global extent of cropland reasonably well, but not recent expansion (1992–2015). Deviations from models of cropland extent in 1992 (“frontierness”) can be used to improve global models of recent expansion, most likely as these deviations are a proxy for cropland expansion under frontier conditions where classical economic theories of expansion are less applicable. Frontierness is insensitive to the land cover dataset used and is particularly effective in improving models that include mosaic land cover classes and the largely smallholder-driven frontier expansion occurring in such areas. Our findings have important implications as the frontierness approach offers a straightforward way to improve global land use change models.

A GIS-Based Approach to Inform Agriculture-Water-Energy Nexus Planning in the North Western Sahara Aquifer System (NWSAS)

The North Western Sahara Aquifer System (NWSAS) is a vital groundwater source in a notably water-scarce region. However, impetuous agricultural expansion and poor resource management (e.g., over-irrigation, inefficient techniques) over the past decades have raised a number of challenges. In this exploratory study, we introduce an open access GIS-based model to help answer selected timely questions related to the agriculture, water and energy nexus in the region. First, the model uses spatial and tabular data to identify the location and extent of irrigated cropland. Then, it employs spatially explicit climatic datasets and mathematical formulation to estimate water and electricity requirements for groundwater irrigation in all identified locations. Finally, it evaluates selected supply options to meet the electricity demand and suggests the least-cost configuration in each location. Results indicate that full irrigation in the basin requires ~3.25 billion million m3 per year. This translates to ~730 GWh of electricity. Fossil fuels do provide the least-cost electricity supply option due to lower capital and subsidized operating costs. Hence, to improve the competitiveness of renewable technologies (RT) (i.e., solar), a support scheme to drop the capital cost of RTs is critically needed. Finally, moving towards drip irrigation can lead to ~47% of water abstraction savings in the NWSAS area.

Multiple cropping systems of the world and the potential for increasing cropping intensity

Multiple cropping, defined as harvesting more than once a year, is a widespread land management strategy in tropical and subtropical agriculture. It is a way of intensifying agricultural production and diversifying the crop mix for economic and environmental benefits. Here we present the first global gridded data set of multiple cropping systems and quantify the physical area of more than 200 systems, the global multiple cropping area and the potential for increasing cropping intensity. We use national and sub-national data on monthly crop-specific growing areas around the year 2000 (1998–2002) for 26 crop groups, global cropland extent and crop harvested areas to identify sequential cropping systems of two or three crops with non-overlapping growing seasons. We find multiple cropping systems on 135 million hectares (12% of global cropland) with 85 million hectares in irrigated agriculture. 34%, 13% and 10% of the rice, wheat and maize area, respectively are under multiple cropping, demonstrating the importance of such cropping systems for cereal production. Harvesting currently single cropped areas a second time could increase global harvested areas by 87–395 million hectares, which is about 45% lower than previous estimates. Some scenarios of intensification indicate that it could be enough land to avoid expanding physical cropland into other land uses but attainable intensification will depend on the local context and the crop yields attainable in the second cycle and its related environmental costs.

A cultivated planet in 2010 – Part 1: The global synergy cropland map

Abstract. Information on global cropland distribution and agricultural production is critical for the world's agricultural monitoring and food security. We present datasets of cropland extent and agricultural production in a two-paper series of a cultivated planet in 2010. In the first part, we propose a new Self-adapting Statistics Allocation Model (SASAM) to develop the global map of cropland distribution. SASAM is based on the fusion of multiple existing cropland maps and multilevel statistics of the cropland area, which is independent of training samples. First, cropland area statistics are used to rank the input cropland maps, and then a scoring table is built to indicate the agreement among the input datasets. Secondly, statistics are allocated adaptively to the pixels with higher agreement scores until the cumulative cropland area is close to the statistics. The multilevel allocation results are then integrated to obtain the extent of cropland. We applied SASAM to produce a global cropland synergy map with a 500 m spatial resolution for circa 2010. The accuracy assessments show that the synergy map has higher accuracy than the input datasets and better consistency with the cropland statistics. The synergy cropland map is available via an open-data repository (https://doi.org/10.7910/DVN/ZWSFAA; Lu et al., 2020). This new cropland map has been used as an essential input to the Spatial Production Allocation Model (SPAM) for producing the global dataset of agricultural production for circa 2010, which is described in the second part of the two-paper series.

Mapping croplands of Europe, Middle East, Russia, and Central Asia using Landsat, Random Forest, and Google Earth Engine

Accurate and timely information on croplands is important for environmental, food security, and policy studies. Spatially explicit cropland datasets are also required to derive information on crop type, crop yield, cropping intensity, as well as irrigated areas. Large area – defined as continental to global – cropland mapping is challenging due to differential manifestation of croplands, wide range of cultivation practices and limited reference data availability. This study presents the results of a cropland extent mapping of 64 countries covering large parts of Europe, Middle East, Russia and Central Asia. To cover such a vast area, roughly 160,000 Landsat scenes from 3351 footprints between 2014 and 2016 were processed within the Google Earth Engine (GEE) platform. We used a pixel-based Random Forest (RF) machine learning algorithm with a set of satellite data inputs capturing diverse spectral, temporal and topographical characteristics across twelve agroecological zones (AEZs). The reference data to train the classification model were collected from very high spatial resolution imagery (VHRI) and ancillary datasets. The result is a binary map showing cultivated/non-cultivated areas ca. 2015. The map produced an overall accuracy of 93.8% with roughly 14% omission and commission errors for the cropland class based on a large set of independent validation samples. The map suggests the entire study area has a total 546 million hectares (Mha) of net croplands (nearly 30% of global net cropland areas) occupying 18% of the study land area. Comparison between national cropland area estimates from United Nations Food and Agricultural Organizations (FAO) and those derived from this work also showed an R-square value of 0.95. This Landsat-derived 30-m cropland product (GFSAD30) provided 10–30% greater cropland areas compared to UN FAO in the 64 Countries. Finally, the map-to-map comparison between GFSAD30 with several other cropland products revealed that the best similarity matrix was with the 30 m global land cover (GLC30) product providing an overall similarity of 88.8% (Kappa 0.7) with producer’s cropland similarity of 89.2% (errors of omissions = 10.8%) and user’s cropland similarity of 81.8% (errors of commissions = 8.1%). GFSAD30 captured the missing croplands in GLC30 product around significantly irrigated agricultural areas in Germany and Belgium and rainfed agriculture in Italy. This study also established that the real strengths of GFSAD30 product, compared to other products, were: 1. identifying precise location of croplands, and 2. capturing fragmented croplands. The cropland extent map dataset is available through NASA’s Land Processes Distributed Active Archive Center (LP DAAC) at https://doi.org/10.5067/MEaSUREs/GFSAD/GFSAD30EUCEARUMECE.001, while the training and reference data as well as visualization are available at the Global Croplands <https://croplands.org> website, GEE code is accessible at: https://code.earthengine.google.com/1666e8bed34e0ce2b2aaf1235ad8c6bd.

Comparison of Different Cropland Classification Methods under Diversified Agroecological Conditions in the Zambezi River Basin

Having updated knowledge of cropland extent is essential for crop monitoring and food security early warning. Previous research has proposed different methods and adopted various datasets for mapping cropland areas at regional to global scales. However, most approaches did not consider the characteristics of farming systems and apply the same classification method in different agroecological zones (AEZs). Furthermore, the acquisition of in situ samples for classification training remains challenging. To address these knowledge gaps and challenges, this study applied a zone-specific classification by comparing four classifiers (random forest, the support vector machine (SVM), the classification and regression tree (CART) and minimum distance) for cropland mapping over four different AEZs in the Zambezi River basin (ZRB). Landsat-8 and Sentinel-2 data and derived indices were used and synthesized to generate thirty-five layers for classification on the Google Earth Engine platform. Training samples were derived from three existing landcover datasets to minimize the cost of sample acquisitions over the large area. The final cropland map was generated at a 10 m resolution. The performance of the four classifiers and the viability of training samples were analysed. All classifiers presented higher accuracy in cool AEZs than in warm AEZs, which may be attributed to field size and lower confusion between cropland and grassland classes. This indicates that agricultural landscape may impact classification results regardless of the classifiers. Random forest was found to be the most stable and accurate classifier across different agricultural systems, with an overall accuracy of 84% and a kappa coefficient of 0.67. Samples extracted over the full agreement areas among existing datasets reduced uncertainty and provided reliable calibration sets as a replacement of costly in situ measurements. The methodology proposed by this study can be used to generate periodical high-resolution cropland maps in ZRB, which is helpful for the analysis of cropland extension and abandonment as well as intensity changes in response to the escalating population and food insecurity.

A generalized approach based on convolutional neural networks for large area cropland mapping at very high resolution

Timely and accurate delineation of the cropland extent over large area is crucial for operational agriculture monitoring and is also beneficial to address food security issues. Existing global datasets associated with cropland are limited by insufficient spatial resolution to properly represent areas with small parcel size distributions, and their less-than-ideal accuracies hamper application at regional and local scales. Diverse very high spatial resolution (VHSR) satellite systems are now available, offering sub-meter to five-meter resolution (e.g. Gaofen-1, Gaofen-2, and ZiYuan-3), and hence enabling explicit extraction of cropland areas from heterogeneous and fragmented landscapes. This study presented a generalized methodology for operational cropland mapping at very high resolution using a deep convolutional neural network to automatically learn the robust and discriminative features. Specifically, we slightly modified the pyramid scene parsing network (PSPNet) and combined deep long-range features with shadow local features to provide predictions with high level of detail. We demonstrated the modified PSPNet (MPSPNet) over four province-wide study areas (Heilongjiang, Hebei, Zhejiang and Guangdong) with diverse agrosystems across China from north to south using multi-source very high spatial resolution satellite images (mainly Gaofen-1 supplemented with Gaofen-2 and ZiYuan-3), with the overall accuracies ranging from 89.99% to 92.31%. Moreover, we compared MPSPNet with other CNN models and investigated the its behavior by visualizing the learned features on different layers, indicating that combining low and high level features for final classification was an efficient and accurate strategy for cropland mapping because the former capture edge information related to object boundaries and the latter could learn long-range spatial dependencies that helped recognize croplands. The temporal transfer and spatial transfer assessments from the respects of qualitative and quantitative corroborated the robust generalizability of the proposed method. And the contrast to the traditional object-based classification method also demonstrated the advantages and strong generalization capabilities of MPSPNet in extracting cropland using VHSR remote sensed images. We compared our results with the current cropland maps generated from FROM-GLC10, which further verified the effectiveness of the proposed approach for large-scale cropland mapping at very high resolution.

Large climate mitigation potential from adding trees to agricultural lands.

While improved management of agricultural landscapes is promoted as a promising natural climate solution, available estimates of the mitigation potential are based on coarse assessments of both agricultural extent and aboveground carbon density. Here we combine 30 meter resolution global maps of aboveground woody carbon, tree cover, and cropland extent, as well as a 1km resolution map of global pasture land, to estimate the current and potential carbon storage of trees in nonforested portions of agricultural lands. We find that global croplands currently store 3.07Pg of carbon (C) in aboveground woody biomass (i.e., trees) and pasture lands account for an additional 3.86PgC across a combined 3.76billion ha. We then estimate the climate mitigation potential of multiple scenarios of integration and avoided loss of trees in crop and pasture lands based on region-specific biomass distributions. We evaluate our findings in the context of nationally determined contributions and find that the majority of potential carbon storage from integration and avoided loss of trees in crop and pasture lands is in countries that do not identify agroforestry as a climate mitigation technique.

A High-Resolution Cropland Map for the West African Sahel Based on High-Density Training Data, Google Earth Engine, and Locally Optimized Machine Learning

The West African Sahel Cropland map (WASC30) is a new 30-m cropland extent product for the nominal year of 2015. We used the computing resources provided by Google Earth Engine (GEE) to fit and apply Random Forest models for cropland detection in each of 189 grid cells (composed of 100 km2, hence a total of ~1.9 × 106 km2) across five countries of the West African Sahel (Burkina Faso, Mauritania, Mali, Niger, and Senegal). Landsat-8 surface reflectance (Bands 2–7) and vegetation indices (NDVI, EVI, SAVI, and MSAVI), organized to include dry-season and growing-season band reflectances and vegetation indices for the years 2013–2015, were used as predictors. Training data were derived from an independent, high-resolution, visually interpreted sample dataset that classifies sample points across West Africa using a 2-km grid (~380,000 points were used in this study, with 50% used for model training and 50% used for model validation). Analysis of the new cropland dataset indicates a summed cropland area of ~316 × 103 km2 across the 5 countries, primarily in rainfed cropland (309 × 103 km2), with irrigated cropland area (7 × 103 km2) representing 2% of the total cropland area. At regional scale, the cropland dataset has an overall accuracy of 90.1% and a cropland class (rainfed and irrigated) user’s accuracy of 79%. At bioclimatic zones scale, results show that land proportion occupied by rainfed agriculture increases with annual precipitation up to 1000 mm. The Sudanian zone (600–1200 mm) has the highest proportion of land in agriculture (24%), followed by the Sahelian (200–600 mm) and the Guinean (1200 +) zones for 15% and 4%, respectively. The new West African Sahel dataset is made freely available for applications requiring improved cropland area information for agricultural monitoring and food security applications.

Vegetation Fraction Images Derived from PROBA-V Data for Rapid Assessment of Annual Croplands in Brazil

This paper presents a new method for rapid assessment of the extent of annual croplands in Brazil. The proposed method applies a linear spectral mixing model (LSMM) to PROBA-V time series images to derive vegetation, soil, and shade fraction images for regional analysis. We used S10-TOC (10 days synthesis, 1 km spatial resolution, and top-of-canopy) products for Brazil and S5-TOC (five days synthesis, 100 m spatial resolution, and top-of-canopy) products for Mato Grosso State (Brazilian Legal Amazon). Using the time series of the vegetation fraction images of the whole year (2015 in this case), only one mosaic composed with maximum values of vegetation fraction was generated, allowing detecting and mapping semi-automatically the areas occupied by annual crops during the year. The results (100 m spatial resolution map) for the Mato Grosso State were compared with existing global datasets (Finer Resolution Observation and Monitoring—Global Land Cover (FROM-GLC) and Global Food Security—Support Analyses Data (GFSAD30)). Visually those maps present a good agreement, but the area estimated are not comparable since the agricultural class definition are different for those maps. In addition, we found 11.8 million ha of agricultural areas in the entire Brazilian territory. The area estimation for the Mato Grosso State was 3.4 million ha for 1 km dataset and 5.3 million ha for 100 m dataset. This difference is due to the spatial resolution of the PROBA-V datasets used. A coefficient of determination of 0.82 was found between PROBA-V 100 m and Landsat-8 OLI area estimations for the Mato Grosso State. Therefore, the proposed method is suitable for detecting and mapping annual croplands distribution operationally using PROBA-V datasets for regional analysis.

Dry cropland changes in China's Three Gorges Reservoir Region during the period 1990 to 2015

Monitoring and analyzing changes in the extent of cultivated land may inform strategic decisions on issues of environmental and food security. The dry cropland area of 12000 km2 in the Three Gorges Reservoir Region (TGRR) of China is essential for feeding the local population of ≈20 million, but is highly prone to soil erosion, leading to the delivery of excessive amounts of sediment and associated pollutants to the Three Gorges Reservoir (TGR), and causing serious eco-environmental consequences. Against this background, this paper used Landsat images and a digital elevation model to analyze the altitudinal distribution of, and dynamic changes in, the area of dry cropland during the period 1990 to 2015. The results suggest that dry cropland was mainly distributed in the elevation range of 200-600 m. The dry cropland area decreased from 12525.37 km2 to 11796.27 km2 during the 25-year study period, including a particularly significant decrease in the rate of decrease from 6.93 km2/yr to 43.99 km2/yr after 2000. The largest decline in the dry cropland area occurred in the elevation range of 600-900 m. The transformations between dry cropland and forest revealed the impact of the TGR operation on the extent of dry cropland. A total of 528.79 km2 of dry cropland with slopes >25° were converted to forest after 2000, whereas a total of 642 km2 of forest was converted to dry cropland during the study period, and these conversions mainly occurred between the elevation of 200–900 m. These spatiotemporal changes in the dry cropland area are likely to raise new issues concerning food security in the TGRR.

Estimating the Potential for Conservation and Farming in the Amazon and Cerrado under Four Policy Scenarios

Since 2013, clearing rates have rapidly increased in the Amazon and Cerrado biomes. This acceleration has raised questions about the efficacy of current regional public and private conservation policies that seek to promote agricultural production while conserving remnants of natural vegetation. In this study, we assessed conservation and agricultural outcomes of four potential policy scenarios that represent perfect adherence to private sector, zero-deforestation commitments (i.e., the Amazon soy moratorium—ASM and the Amazon cattle agreements—CA) and to varying levels of implementation of the Brazilian Forest Code (FC). Under a zero-clearing scenario, we find that the extent of croplands as of 2017 within the two biomes (31 MHa) could double without further clearing if agriculture were to expand on all previously cleared land that is suitable for crops. Moreover, at least 47 MHa of land that is already cleared but unsuitable for crops would remain available for pasture. Under scenarios in which only legal clearing under the FC could occur, 51 MHa of additional natural vegetation could be cleared. This includes as many as 1 MHa of nonforest vegetation that could be cleared in the Amazon biome without triggering the ASM and CA monitoring systems. Two-thirds of the total vegetation vulnerable to legal clearing is located within the Cerrado biome, and 19 MHa of this land is suitable for cropland expansion. Legal clearing of all of these areas could reduce biodiversity persistence by 4% within the two biomes, when compared with the zero-clearing scenario, and release up to 9 PgCO2e, with the majority (75%) coming from the Cerrado biome. However, when we considered the potential outcomes of full implementation of the FC, we found that 22% (11 MHa) of the 51 MHa of vegetation subject to legal clearing could be protected through the environmental quotas market, while an additional 1 MHa should be replanted across the two biomes, predominantly in the Amazon biome (73% of the area subject to replanting). Together, quotas and replanting could prevent the release of 2 PgCO2e that would otherwise be emitted if all legal clearing occurred. Based on our results, we conclude that ongoing legal clearing could create additional space for cropland and cattle production beyond the substantial existing stocks of cleared areas but would significantly impair local carbon and biodiversity stocks.

A blended census and multiscale remote sensing approach to probabilistic cropland mapping in complex landscapes

Remote sensing data are used to map the extent of croplands. They are especially useful in sub-Saharan Africa (SSA) where landscapes are complex and farms are small, i.e. less than two ha. In this study, a hierarchical remote sensing approach was developed to estimate field fractions at 30 m spatial resolution in a highly fragmented agricultural region of Ethiopia. The landscape was stratified into crop production system (CPS) zones with ten-day SPOT Proba-V 1 km normalized difference vegetation index (NDVI) composites. The CPS zones were used to disaggregate agricultural census statistics to 1 km field fractions and mask “wet” and “dry” seasons. Long-term average wet-dry season NDVI and topographic information derived from 30 m Landsat-8 (OLI) surface reflectance and the SRTM digital elevation model were combined with 1 km field fractions in a Generalized Additive Model (GAM) to produce the field fractions. Sample dot grids were manually interpreted from very high-resolution DigitalGlobe imagery on the Google Earth platform for training and testing. The model yielded an Area Under the Curve (AUC) of 0.71 and R2 of 0.65 in the holdout sample set. The high AUC reveals the model was effective at classifying 30 m pixels as “crop” or “not crop” while the high R2 indicated leveraging at the extremes (100 and 0% probability), meaning at 30 m resolution, subpixel variations were difficult to discern. The improved model skill compared to previous cropland mapping studies using GAMs can be attributed to the stratification and decomposition of the Landsat time series using CPS-defined phenology. Additional remote sensing model inputs, such as Sentinel-1 radar backscatter and Sentinel-2 red-edge reflectance, could provide additional explanatory power. Wall-to-wall national coverage for agricultural production estimation or other food security related application could be achieved by manually digitizing additional sample data in other regions of Ethiopia or using existing crowd-sourced databases, such as Geo-Wiki.

Agricultural cropland extent and areas of South Asia derived using Landsat satellite 30-m time-series big-data using random forest machine learning algorithms on the Google Earth Engine cloud

ABSTRACT The South Asia (India, Pakistan, Bangladesh, Nepal, Sri Lanka and Bhutan) has a staggering 900 million people (~43% of the population) who face food insecurity or severe food insecurity as per United Nations, Food and Agriculture Organization’s (FAO) the Food Insecurity Experience Scale (FIES). The existing coarse-resolution (≥250-m) cropland maps lack precision in geo-location of individual farms and have low map accuracies. This also results in uncertainties in cropland areas calculated from such products. Thereby, the overarching goal of this study was to develop a high spatial resolution (30-m or better) baseline cropland extent product of South Asia for the year 2015 using Landsat satellite time-series big-data and machine learning algorithms (MLAs) on the Google Earth Engine (GEE) cloud computing platform. To eliminate the impact of clouds, 10 time-composited Landsat bands (blue, green, red, NIR, SWIR1, SWIR2, Thermal, EVI, NDVI, NDWI) were derived for each of the three time-periods over 12 months (monsoon: Days of the Year (DOY) 151–300; winter: DOY 301–365 plus 1–60; and summer: DOY 61–150), taking the every 8-day data from Landsat-8 and 7 for the years 2013–2015, for a total of 30-bands plus global digital elevation model (GDEM) derived slope band. This 31-band mega-file big data-cube was composed for each of the five agro-ecological zones (AEZ’s) of South Asia and formed a baseline data for image classification and analysis. Knowledge-base for the Random Forest (RF) MLAs were developed using spatially well spread-out reference training data (N = 2179) in five AEZs. The classification was performed on GEE for each of the five AEZs using well-established knowledge-base and RF MLAs on the cloud. Map accuracies were measured using independent validation data (N = 1185). The survey showed that the South Asia cropland product had a producer’s accuracy of 89.9% (errors of omissions of 10.1%), user’s accuracy of 95.3% (errors of commission of 4.7%) and an overall accuracy of 88.7%. The National and sub-national (districts) areas computed from this cropland extent product explained 80-96% variability when compared with the National statistics of the South Asian Countries. The full-resolution imagery can be viewed at full-resolution, by zooming-in to any location in South Asia or the world, at www.croplands.org and the cropland products of South Asia downloaded from The Land Processes Distributed Active Archive Center (LP DAAC) of National Aeronautics and Space Administration (NASA) and the United States Geological Survey (USGS): https://lpdaac.usgs.gov/products/gfsad30saafgircev001/.