Integrated crop–livestock systems (ICLS) are among the main viable strategies for sustainable agricultural production. Mapping these systems is crucial for monitoring land use changes in Brazil, ...playing a significant role in promoting sustainable agricultural production. Due to the highly dynamic nature of ICLS management, mapping them is a challenging task. The main objective of this research was to develop a method for mapping ICLS using deep learning algorithms applied on Satellite Image Time Series (SITS) data cubes, which consist of Sentinel-2 (S2) and PlanetScope (PS) satellite images, as well as data fused (DF) from both sensors. This study focused on two Brazilian states with varying landscapes and field sizes. Targeting ICLS, field data were combined with S2 and PS data to build land use and land cover classification models for three sequential agricultural years (2018/2019, 2019/2020, and 2020/2021). We tested three experimental settings to assess the classification performance using S2, PS, and DF data cubes. The test classification algorithms included Random Forest (RF), Temporal Convolutional Neural Network (TempCNN), Residual Network (ResNet), and a Lightweight Temporal Attention Encoder (L-TAE), with the latter incorporating an attention-based model, fusing S2 and PS within the temporal encoders. Experimental results did not show statistically significant differences between the three data sources for both study areas. Nevertheless, the TempCNN outperformed the other classifiers with an overall accuracy above 90% and an F1-Score of 86.6% for the ICLS class. By selecting the best models, we generated annual ICLS maps, including their surrounding landscapes. This study demonstrated the potential of deep learning algorithms and SITS to successfully map dynamic agricultural systems.
Fast and accurate quantification of the available pasture biomass is essential to support grazing management decisions in intensively managed fields. The increasing temporal and spatial resolutions ...offered by the new generation of orbital platforms, such as Planet CubeSat satellites, have improved the capability of monitoring pasture biomass using remotely sensed data. Here, we assessed the feasibility of using spectral and textural information derived from PlanetScope imagery for estimating pasture aboveground biomass (AGB) and canopy height (CH) in intensively managed fields and the potential for enhanced accuracy by applying the extreme gradient boosting (XGBoost) algorithm. Our results demonstrated that the texture measures enhanced AGB and CH estimations compared to the performance obtained using only spectral bands or vegetation indices. The best results were found by employing the XGBoost models based only on texture measures. These models achieved moderately high accuracy to predict pasture AGB and CH, explaining 65% and 89% of AGB (root mean square error (RMSE) = 26.52%) and CH (RMSE = 20.94%) variability, respectively. This study demonstrated the potential of using texture measures to improve the prediction accuracy of AGB and CH models based on high spatiotemporal resolution PlanetScope data in intensively managed mixed pastures.
Regenerative agricultural practices are a suitable path to feed the global population. Integrated Crop–livestock systems (ICLSs) are key approaches once the area provides animal and crop production ...resources. In Brazil, the expectation is to increase the area of ICLS fields by 5 million hectares in the next five years. However, few methods have been tested regarding spatial and temporal scales to map and monitor ICLS fields, and none of these methods use SAR data. Therefore, in this work, we explored the potential of three machine and deep learning algorithms (random forest, long short-term memory, and transformer) to perform early-season (with three-time windows) mapping of ICLS fields. To explore the scalability of the proposed methods, we tested them in two regions with different latitudes, cloud cover rates, field sizes, landscapes, and crop types. Finally, the potential of SAR (Sentinel-1) and optical (Sentinel-2) data was tested. As a result, we found that all proposed algorithms and sensors could correctly map both study sites. For Study Site 1(SS1), we obtained an overall accuracy of 98% using the random forest classifier. For Study Site 2, we obtained an overall accuracy of 99% using the long short-term memory net and the random forest. Further, the early-season experiments were successful for both study sites (with an accuracy higher than 90% for all time windows), and no significant difference in accuracy was found among them. Thus, this study found that it is possible to map ICLSs in the early-season and in different latitudes by using diverse algorithms and sensors.
Grasslands are the largest contributor of nitrous oxide (N
2
O) emissions in the agriculture sector due to livestock excreta and nitrogen fertilizers applied to the soil. Nitrification inhibitors ...(NIs) added to N input have reduced N
2
O emissions, but can show a range of efficiencies depending on climate, soil, and management conditions. A meta-analysis study was conducted to investigate the factors that influence the efficiency of NIs added to fertilizer and excreta in reducing N
2
O emissions, focused on grazing systems. Data from peer-reviewed studies comprising 2164 N
2
O emission factors (EFs) of N inputs with and without NIs addition were compared. The N
2
O EFs varied according to N source (0.0001–8.25%). Overall, NIs reduced the N
2
O EF from N addition by 56.6% (51.1–61.5%), with no difference between NI types (Dicyandiamide—DCD; 3,4-Dimethylpyrazole phosphate—DMPP; and Nitrapyrin) or N source (urine, dung, slurry, and fertilizer). The NIs were more efficient in situations of high N
2
O emissions compared with low; the reduction was 66.0% when EF > 1.5% of N applied compared with 51.9% when EF ≤ 0.5%. DCD was more efficient when applied at rates > 10 kg ha
−1
. NIs were less efficient in urine with lower N content (≤ 7 g kg
−1
). NI efficiency was negatively correlated with soil bulk density, and positively correlated with soil moisture and temperature. Better understanding and management of NIs can optimize N
2
O mitigation in grazing systems, e.g., by mapping N
2
O risk and applying NI at variable rate, contributing to improved livestock sustainability.
To meet rising demands for agricultural products, existing agricultural lands must either produce more or expand in area. Yield gaps (YGs)—the difference between current and potential yield of ...agricultural systems—indicate the ability to increase output while holding land area constant. Here, we assess YGs in global grazed‐only permanent pasture lands using a climate binning approach. We create a snapshot of circa 2000 empirical yields for meat and milk production from cattle, sheep, and goats by sorting pastures into climate bins defined by total annual precipitation and growing degree‐days. We then estimate YGs from intra‐bin yield comparisons. We evaluate YG patterns across three FAO definitions of grazed livestock agroecosystems (arid, humid, and temperate), and groups of animal production systems that vary in animal types and animal products. For all subcategories of grazed‐only permanent pasture assessed, we find potential to increase productivity several‐fold over current levels. However, because productivity of grazed pasture systems is generally low, even large relative increases in yield translated to small absolute gains in global protein production. In our dataset, milk‐focused production systems were found to be seven times as productive as meat‐focused production systems regardless of animal type, while cattle were four times as productive as sheep and goats regardless of animal output type. Sustainable intensification of pasture is most promising for local development, where large relative increases in production can substantially increase incomes or “spare” large amounts of land for other uses. Our results motivate the need for further studies to target agroecological and economic limitations on productivity to improve YG estimates and identify sustainable pathways toward intensification.
We use climate binning to estimate current versus potential protein yield of global, grazed‐only, permanent pasture systems. We create a snapshot of empirical yields for meat and milk production from cattle, sheep, and goats and sort pastures into climate bins defined by total annual precipitation and growing degree‐days (a). Within bins, productivity is ranked from low to high, revealing large yield gaps among regions relative to the highest performing “climate peers” (b). Globally, most of these pastures show potential for several fold increases over current production levels (c), although they remain a low‐yield land use in terms of net food production.
The recent advances in unmanned aerial vehicle (UAV)-based remote sensing systems have broadened the remote sensing applications for agriculture. Despite the great possibilities of using UAVs to ...monitor agricultural fields, specific problems related to missing parts in UAV orthomosaics due to drone flight restrictions are common in agricultural monitoring, especially in large areas. In this study, we propose a methodological framework to impute missing parts of UAV orthomosaics using PlanetScope (PS) and Sentinel-2 (S2) data and the random forest (RF) algorithm of an integrated crop–livestock system (ICLS) covered by grass at the time. We validated the proposed framework by simulating and imputing artificial missing parts in a UAV orthomosaic and then comparing the original data with the model predictions. Spectral bands and the normalized difference vegetation index (NDVI) derived from PS, as well as S2 images (separately and combined), were used as predictor variables of the UAV spectral bands and NDVI in developing the RF-based imputation models. The proposed framework produces highly accurate results (RMSE = 6.77–17.33%) with a computationally efficient and robust machine-learning algorithm that leverages the wealth of empirical information present in optical satellite imagery (PS and S2) to impute up to 50% of missing parts in a UAV orthomosaic.
Process-based models (PBM) are important tools for understanding the benefits of Integrated Crop-Livestock Systems (ICLS), such as increasing land productivity and improving environmental conditions. ...PBM can provide insights into the contribution of agricultural production to climate change and help identify potential greenhouse gas (GHG) mitigation and carbon sequestration options. Rehabilitation of degraded lands is a key strategy for achieving food security goals and can reduce the need for new agricultural land. This study focused on the calibration and validation of the DayCent PBM for a typical ICLS adopted in Brazil from 2018 to 2020. We also present the DayCent parametrization for two forage species (ruzigrass and millet) grown simultaneously, bringing some innovation in the modeling challenges. We used aboveground biomass to calibrate the model, randomly selecting data from 70% of the paddocks in the study area. The calibration obtained a coefficient of determination (R2) of 0.69 and a relative RMSE of 37.0%. During the validation, we used other variables (CO2 flux, grain biomass, and soil water content) measured in the ICLS and performed a double validation for plant growth to evaluate the robustness of the model in terms of generalization. R2 validations ranged from 0.61 to 0.73, and relative RMSE from 11.3 to 48.3%. Despite the complexity and diversity of ICLS results show that DayCent can be used to model ICLS, which is an important step for future regional analyses and large-scale evaluations of the impacts of ICLS.
•There is still an absence of clear definitions about pasture and managed lands.•Brazilian maps discrepancies were due to definitions, methods and harmonization.•Datasets should include a full ...definition of methods, terms and management attributes.•General guidance for the maps addressed the consistency of managed land data.
Pasture land occupies extensive areas and is increasingly of interest for sustainable intensification, land use diversification, greenhouse gas emission mitigation, and bioenergy expansion. Accurate maps of pasture and other managed land covers are needed for monitoring, intercomparison, assessing potential uses, and planning. Yet, land maps can be generated from different types of classification datasets – i.e. as a land use or land cover type – as well as different sources. In this study our aim was to assess and compare land use and land cover definitions for pasture, and examine variability in the resulting pasture land classification maps. First, we conducted a review of pasture definitions in commonly used mapping databases. We then performed a case study involving Brazil, a dominant global producer of pasture-based livestock. Six geospatial databases were harmonized and compared to each other and to MODIS land cover for Brazil including the Cerrado and Amazon biomes, which are internationally recognized for their ecological value. Total pasture area estimates for Brazil ranged by a factor greater than four, from about 430,000 km2 to over 1.7 million km2. Our analysis showed high variability in pasture land maps depending on the definitions, methods and underlying datasets used to generate them. The results are illustrative of a symptomatic problem for all manage land datasets, demonstrating the need for land categories studies and geospatial data resources that fully define land terms and describe measurable management attributes. Additionally, the suitability of individual geospatial datasets for different types of land mapping must be better described and reported. These recommendations would help bring more consistency in the consideration of managed lands in research, reporting, and policy development, as demonstrated here for pasture land using six case study datasets from multiple sources.
Accurate mapping of crops with high spatiotemporal resolution plays a critical role in achieving the Sustainable Development Goals (SDGs), especially in the context of integrated crop-livestock ...systems (ICLS). Stakeholders can make informed decisions and implement targeted strategies to achieve multiple SDGs related to agriculture, rural development, and sustainable livelihoods by understanding the spatial dynamics of these systems. Accurate information on the extent of ICLS derived from multitemporal remote sensing and emerging map techniques such as deep learning can help in the implementation of sustainable agricultural practices. However, far too little attention has been paid to ICLS map accuracy because it may not be at the forefront of research agendas compared to those of other agricultural practices. This paper aims to map ICLS using high spatiotemporal resolution imagery and deep learning neural network classifiers at two different sites located in Brazil. The pipeline involves four interpretation approaches based on the ICLS class: evaluating deep neural network classifiers with different image composition intervals, explaining commission and omission errors, evaluating the temporal transferability of the method, and evaluating the influence of variables. The study area consists of two locations in São Paulo (study site 1, SS1) and Mato Grosso state (study site 2, SS2), Brazil. We derived nine spectral variables from PlanetScope (PS) images and four metrics through object-based image analysis (OBIA) using two time intervals, 10 and 15 days, to generate the image compositions. These input variables were used in three deep neural network classifiers: convolutional neural network in one dimension (Conv1D), long short-term memory (LSTM), and LSTM with a fully convolutional network (LSTM-FCN). Our results showed that mapping dynamic land use such as ICLS is possible by using high-spatiotemporal-resolution imagery and deep neural network classifiers. The 15-day LSTM-FCN classifier returned the highest map accuracies for both sites, with the following class-level accuracies: producer accuracy (PA) = 97.0% and user accuracy (UA) = 97.0% for SS1 and PA = 82.0% and UA = 96.5% for SS2. Meanwhile, we found map uncertainties arising from the diverse crop calendars and spectro-temporal similarities between ICLS and other land use. The best approaches revealed that temporal generalization was suitable for mapping ICLS, but some classifiers could not generalize due to the inherent characteristics of the class. Most variables were considered efficient for predicting ICLS, although spectral indices revealed better functional relationships, while the PS bands had a lower influence on the predictions. The accuracies achieved with the proposed method represent promising opportunities for the sufficiently accurate mapping of ICLS and other complex crop activities.
•A novel approach is proposed for integrated-crop livestock system (ICLS) mapping.•PlanetScope time series and deep learning effectively map ICLS.•Vegetation indices are powerful predictors for ICLS mapping.•ICLS mapping models can be transferred across years to avoid sample collection.
Crop identification is an important task in the process of yield estimation; however, sometimes it can be difficult when using images of medium to low spatial resolution due to mixing of ...heterogeneous areas within the pixel. Therefore, selecting pixels that best represent an area/crop could be an alternative to input data in yield estimate models. The objective of this study was to select soya bean pixels based on temporal stability technique and test the ability of these pixels to predict yield. The study was conducted at county level in Paraná state, Brazil, during 11 years of soya bean growing season. To estimate yield, we created a linear regression model and used accumulated enhanced vegetation index during four periods according to soya bean phenological stages, which are as follows: emergence to maturity, emergence to flowering, flowering to grain filling, and flowering to maturity. Among all periods of the crop season, emergence to flowering showed the lowest precision while flowering to maturity was the period with the best agreements when compared with official data; the root mean square error ranged from 0.07 to 0.37 t ha –¹. The temporal stability method has proven to be an efficient tool to select pixel that could represent the crop for predicting yield. In addition, we could verify the most suitable period for making soya bean yield prediction.