Search

Making plant breeding programs less expensive, fast, practical, and accurate, especially for soybeans, promotes the selection of new soybean genotypes and contributes to the emergence of new varieties that are more efficient in absorbing and metabolizing nutrients. Using spectral information from soybean genotypes combined with nutritional information on secondary macronutrients can help genetic improvement programs select populations that are efficient in absorbing and metabolizing these nutrients. In addition, using machine learning algorithms to process this information makes the acquisition of superior genotypes more accurate. Therefore, the objective of the work was to verify the classification performance of soybean genotypes regarding secondary macronutrients by ML algorithms and different inputs. The experiment was conducted in the experimental area of the Federal University of Mato Grosso do Sul, municipality of Chapadão do Sul, Brazil. Soybean was sown in the 2019/20 crop season, with the planting of 103 F2 soybean populations. The experimental design used was randomized blocks, with two replications. At 60 days after crop emergence (DAE), spectral images were collected with a Sensifly eBee RTK fixed-wing remotely piloted aircraft (RPA), with autonomous takeoff control, flight plan, and landing. At the reproductive stage (R1), three leaves were collected per plant to determine the macronutrients calcium (Ca), magnesium (Mg), and sulfur (S) levels. The data obtained from the spectral information and the nutritional values of the genotypes in relation to Ca, Mg, and S were subjected to a Pearson correlation analysis; a PC analysis was carried out with a k-means algorithm to divide the genotypes into clusters. The clusters were taken as output variables, while the spectral data were used as input variables for the classification models in the machine learning analyses. The configurations tested in the models were spectral bands (SBs), vegetation indices (VIs), and a combination of both. The combination of machine learning algorithms with spectral data can provide important biological information about soybean plants. The classification of soybean genotypes according to calcium, magnesium, and sulfur content can maximize time, effort, and labor in field evaluations in genetic improvement programs. Therefore, the use of spectral bands as input data in random forest algorithms makes the process of classifying soybean genotypes in terms of secondary macronutrients efficient and important for researchers in the field. [ABSTRACT FROM AUTHOR]

Plants respond to biotic and abiotic pressures by changing their biophysical and biochemical aspects, such as reducing their biomass and developing chlorosis, which can be readily identified using remote-sensing techniques applied to the VIS/NIR/SWIR spectrum range. In the current scenario of agriculture, production efficiency is fundamental for farmers, but diseases such as target spot continue to harm soybean yield. Remote sensing, especially hyperspectral sensing, can detect these diseases, but has disadvantages such as cost and complexity, thus favoring the use of UAVs in these activities, as they are more economical. The objectives of this study were: (i) to identify the most appropriate input variable (bands, vegetation indices and all reflectance ranges) for the metrics assessed in machine learning models; (ii) to verify whether there is a statistical difference in the response of NDVI (normalized difference vegetation index), grain weight and yield when subjected to different levels of severity; and (iii) to identify whether there is a relationship between the spectral bands and vegetation indices with the levels of target spot severity, grain weight and yield. The field experiment was carried out in the 2022/23 crop season and involved different fungicide treatments to obtain different levels of disease severity. A spectroradiometer and UAV (unmanned aerial vehicle) imagery were used to collect spectral data from the leaves. Data were subjected to machine learning analysis using different algorithms. LR (logistic regression) and SVM (support vector machine) algorithms performed better in classifying target spot severity levels when spectral data were used. Multivariate canonical analysis showed that healthy leaves stood out at specific wavelengths, while diseased leaves showed different spectral patterns. Disease detection using hyperspectral sensors enabled detailed information acquisition. Our findings reveal that remote sensing, especially using hyperspectral sensors and machine learning techniques, can be effective in the early detection and monitoring of target spot in the soybean crop, enabling fast decision-making for the control and prevention of yield losses. [ABSTRACT FROM AUTHOR]

In recent years, agricultural remote sensing technology has made great progress. The availability of sensors capable of detecting electromagnetic energy and/or heat emitted by targets improves the pre-harvest process and therefore becomes an indispensable tool in the post-harvest phase. Therefore, we outline how remote sensing tools can support a range of agricultural processes from field to storage through crop yield estimation, grain quality monitoring, storage unit identification and characterization, and production process planning. The use of sensors in the field and post-harvest processes allows for accurate real-time monitoring of operations and grain quality, enabling decision-making supported by computer tools such as the Internet of Things (IoT) and artificial intelligence algorithms. This way, grain producers can get ahead, track and reduce losses, and maintain grain quality from field to consumer. [ABSTRACT FROM AUTHOR]

Assessing different levels of red gum lerp psyllid (Glycaspis brimblecombei) can influence the hyperspectral reflectance of leaves in different ways due to changes in chlorophyll. In order to classify these levels, the use of machine learning (ML) algorithms can help process the data faster and more accurately. The objectives were: (I) to evaluate the spectral behavior of the G. brimblecombei attack levels; (II) find the most accurate ML algorithm for classifying pest attack levels; (III) find the input configuration that improves performance of the algorithms. Data were collected from a clonal eucalyptus plantation (clone AEC 0144—Eucalyptus urophilla) aged 10.3 months old. Eighty sample evaluations were carried out considering the following severity levels: control (no shells), low infestation (N1), intermediate infestation (N2), and high infestation (N3), for which leaf spectral reflectances were obtained using a spectroradiometer. The spectral range acquired by the equipment was 350 to 2500 nm. After obtaining the wavelengths, they were grouped into representative interval means in 28 bands. Data were submitted to the following ML algorithms: artificial neural networks (ANN), REPTree (DT) and J48 decision trees, random forest (RF), support vector machine (SVM), and conventional logistic regression (LR) analysis. Two input configurations were tested: using only the wavelengths (ALL) and using the spectral bands (SB) to classify the attack levels. The output variable was the severity of G. brimblecombei attack. There were differences in the hyperspectral behavior of the leaves for the different attack levels. The highest attack level shows the greatest distinction and the highest reflectance values. LR and SVM show better accuracy in classifying the severity levels of G. brimblecombei attack. For the correct classification percentage, the RL and SVM algorithms performed better, both with accuracy above 90%. Both algorithms achieved F-score values close to 0.90 and above 0.8 for Kappa. The entire spectral range guaranteed the best accuracy for both algorithms. [ABSTRACT FROM AUTHOR]

Predicting maize yield using spectral information, temperature, and different irrigation management through machine learning algorithms provide information in a fast, accurate, and non-destructive way. The use of multispectral sensor data coupled with irrigation management in maize allows further exploration of water behavior and its relationship with changes in spectral bands presented by the crop. Thus, the objective of this study was to evaluate, by means of multivariate statistics and machine learning techniques, the relationship between irrigation management and spectral bands in predicting maize yields. Field experiments were carried out over two seasons (first and second seasons) in a randomized block design with four treatments (control and three additional irrigation levels) and eighteen sample repetitions. The response variables analyzed were vegetation indices (IVs) and crop yield (GY). Measurement of spectral wavelengths was performed with the Sensefly eBee RTK, with autonomous flight control. The eBee was equipped with the Parrot Sequoia multispectral sensor acquiring reflectance at the wavelengths of green (550 nm ± 40 nm), red (660 nm ± 40 nm), red-edge (735 nm ± 10 nm), and NIR (790 nm ± 40 nm). The blue length (496 nm) was obtained by additional RGB imaging. Data were subjected to Pearson correlations (r) between the evaluated variables represented by a correlation and scatter plot. Subsequently, the canonical analysis was performed to verify the interrelationship between the variables evaluated. Data were also subjected to machine learning (ML) analysis, in which three different input dataset configurations were tested: using only irrigation management (IR), using irrigation management and spectral bands (SB+IR), and using irrigation management, spectral bands, and temperature (IR+SB+Temp). ML models used were: Artificial Neural Network (ANN), M5P Decision Tree (J48), REPTree Decision Tree (REPT), Random Forest (RF), and Support Vector Machine (SVM). A multiple linear regression (LR) was tested as a control model. Our results revealed that Random Forest has higher accuracy in predicting grain yield in maize, especially when associated with the inputs SB+IR and SB+IR+Temp. [ABSTRACT FROM AUTHOR]

Using remote sensing combined with machine learning (ML) techniques is a promising approach to classify soybean cultivars. Therefore, the objectives of this study are (i) to verify which input dataset configuration (using only spectral bands, only vegetation indices, or both) is more accurate in the identification of soybean cultivars, and (ii) to verify which ML technique is more accurate in the identification of soybean cultivars. Information was extracted from five central irrigation pivots in the same region and with the same sowing date in the 2015/2016 crop year, in which each pivot was cultivated with a different cultivar, in which the cultivars used were: CV1—P98y12 RR, CV2—Desafio RR, CV3—M6410 IPRO, CV4—M7110 IPRO, and CV5—NA5909 RR. A cloud-free orbital image of the site was acquired from the Google Earth Engine platform. In addition to the spectral bands alone, a total of 13 vegetation indices were calculated. The models tested were: artificial neural networks (ANN), radial basis function network (RBF), decision tree algorithms J48 (DT) and reduced error pruning tree (REP), random forest (RF), and support vector machine (SVM). The five soybean cultivars were classified by the six-machine learning (ML) models in stratified randomized cross-validation with k-fold = 10 and 10 repetitions (100 runs for each model). After obtaining the r and MAE statistics, analysis of variance was performed considering a 6 × 3 factorial scheme (models versus inputs) with 10 repetitions (folds). The means were grouped by the Scott–Knott test at 5% probability. The spectral bands were the most accurate among the tested inputs in the identification of soybean cultivars. ANN was the most accurate model in identifying soybean cultivars. [ABSTRACT FROM AUTHOR]

In recent years, Brazil has become a major global contributor to the occurrence of national fires and greenhouse gas emissions. Therefore, this study aimed to evaluate the fire foci data of the past 20 years to determine their relationship with climatic variables in various Brazilian regions. The variables evaluated included fire foci, land surface temperature, rainfall, and standardized precipitation index, which were obtained via remote sensing from 2000 to 2019. The data were subjected to trend analyses (Mann–Kendall and Pettitt tests) and a multivariate analysis of canonical variables for evaluation. The results showed that the Midwest and North regions had the highest occurrence of fire foci throughout the study period, and that the North region had the highest accumulated annual rainfall. Thus, these regions require specific public policies to prevent future fires. Overall, the Midwest, Southeast, and South regions exhibit significant increasing fire foci tendencies. Our results reveal that this trend is related to the El Niño-Southern Oscillation (ENSO) phenomena, which alter climatic variables such as precipitation, land surface temperature, and the standardized precipitation index. Finally, the sugarcane growing area had a significant linear relationship with fire foci in the Southeast region, especially in the state of São Paulo, the major national sugarcane producer. [ABSTRACT FROM AUTHOR]

The guidance on decision-making regarding deforestation in Amazonia has been efficient as a result of monitoring programs using remote sensing techniques. Thus, the objective of this study was to identify the expansion of soybean farming in disagreement with the Soy Moratorium (SoyM) in the Amazonia biome of Mato Grosso from 2008 to 2019. Deforestation data provided by two Amazonia monitoring programs were used: PRODES (Program for Calculating Deforestation in Amazonia) and ImazonGeo (Geoinformation Program on Amazonia). For the identification of soybean areas, the Perpendicular Crop Enhancement Index (PCEI) spectral model was calculated using a cloud platform. To verify areas (polygons) of largest converted forest-soybean occurrences, the Kernel Density (KD) estimator was applied. Mann–Kendall and Pettitt tests were used to identify trends over the time series. Our findings reveal that 1,387,288 ha were deforested from August 2008 to October 2019 according to PRODES data, of which 108,411 ha (7.81%) were converted into soybean. The ImazonGeo data showed 729,204 hectares deforested and 46,182 hectares (6.33%) converted into soybean areas. Based on the deforestation polygons of the two databases, the KD estimator indicated that the municipalities of Feliz Natal, Tabaporã, Nova Ubiratã, and União do Sul presented higher occurrences of soybean fields in disagreement with the SoyM. The results indicate that the PRODES system presents higher data variability and means statistically superior to ImazonGeo. [ABSTRACT FROM AUTHOR]

The search for high‐yielding genotypes and that are tolerant to abiotic stresses has been a major goal in plant breeding. Thus, the use of technologies such as precision agriculture associated with remote sensing tools for plant phenotyping has increased. The hypothesis of this research was that soya bean genotypes respond differently to low and adequate base saturation levels in the soil and that vegetation indexes can be efficient auxiliary tools in plant phenotyping for this purpose. The objective of this study was to evaluate the nutritional status and agronomic performance of soya bean genotypes grown in low and recommended base saturation conditions using high‐throughput phenotyping. The research was carried out in 2017/2018 and 2018/2019 crop seasons, in which two field experiments in each season were installed. In experiment I, genotypes (P1, P2, P3, P4, P5, P6, P7, P8, P9 and P10) were evaluated without soil correction (low saturation condition). In experiment II, liming was performed three months before sowing of the genotypes to raise the base saturation to 60% (recommended saturation). Canopy spectral behaviour at the following wavelengths was evaluated: green (550 nm), red (660 nm), red edge (735 nm) and near‐infrared (790 nm), and the vegetation indices (Vis) NDVI, SAVI, EVI and MSAVI were calculated. The variables evaluated were leaf calcium and magnesium contents and grain yield. The use of VI's was efficient in assessing the performance of genotypes soya bean at different base saturation levels. The EVI showed moderate correlation with the nutritional and agronomic variables measured in each base saturation level. The approach used enabled both to identify genotypes tolerant to low base saturation soils and the ones with better response to liming. [ABSTRACT FROM AUTHOR]

The collapse of mining tailing dams in Brumadinho, Minas Gerais, Brazil, that occurred in 2019 was one of the worst environmental and social disasters witnessed in the country. In this sense, monitoring any impacted areas both before and after the disaster is crucial to understand the actual scenario and problems of disaster management and environmental impact assessment. In order to find answers to that problem, the aim of this study was to identify and analyze the spatiality of the impacted area by rupture of the tailing dam of the Córrego do Feijão mine in Brumadinho, Minas Gerais, by using orbital remote sensing. Land use and land occupation, phytoplankton chlorophyll-a, water turbidity, total suspended solids on water, and carbon sequestration efficiency by vegetation (CO2Flux) were estimated by orbital imagery from the Landsat-8/OLI and MSI/Sentinel-2 sensors in order to assess the environmental impacts generated by the disaster. Data were extracted from spectral models in which the variables that best demonstrated the land use variation over the years were sought. Mean comparison by t-test was performed to compare the time series analyzed, that is, before and after the disaster. Through the analysis of water quality, it was observed that the environmental impact was calamitous to natural resources, especially water from Córrego do Feijão. [ABSTRACT FROM AUTHOR]

The aims of this study were: i) to compare no-till areas in two municipalities located in different regions of Brazil, along with the influence on CO2Flux and GPP, and ii) to verify the difference between environmental factors followed by the trends of these variables regarding future scenarios (ARIMA time-series model number). The study was carried out in two areas with different latitudes in the municipalities of Sinop-MT and Passo Fundo-RS, both in Brazil. A time series of 19 years was performed with data acquired by remote sensing from the following satellites: i) Landsat-8 (OLI and TIRS), and ii) TERRA/AQUA (MODIS). The results propound that the spectro-temporal variables are directly influenced by soil management and agricultural practices over the observation time, with a satisfactory correlation in future predictions of the variables for the next ten years, in which presented that the variation of GPP and albedo values for the two study sites would gradually increase until 2028 and the temperature remained constant between the range of its seasonality, and CO2Flux tends to decrease in its seasonality, indicating a higher CO2 absorption. [ABSTRACT FROM AUTHOR]

The Amazon Basin is undergoing extensive environmental degradation as a result of deforestation and the rising occurrence of fires. The degradation caused by fires is exacerbated by the occurrence of anomalously dry periods in the Amazon Basin. The objectives of this study were: (i) to quantify the extent of areas that burned between 2001 and 2019 and relate them to extreme drought events in a 20-year time series; (ii) to identify the proportion of countries comprising the Amazon Basin in which environmental degradation was strongly observed, relating the spatial patterns of fires; and (iii) examine the Amazon Basin carbon balance following the occurrence of fires. To this end, the following variables were evaluated by remote sensing between 2001 and 2019: gross primary production, standardized precipitation index, burned areas, fire foci, and carbon emissions. During the examined period, fires affected 23.78% of the total Amazon Basin. Brazil had the largest affected area (220,087 fire foci, 773,360 km2 burned area, 54.7% of the total burned in the Amazon Basin), followed by Bolivia (102,499 fire foci, 571,250 km2 burned area, 40.4%). Overall, these fires have not only affected forests in agricultural frontier areas (76.91%), but also those in indigenous lands (17.16%) and conservation units (5.93%), which are recognized as biodiversity conservation areas. During the study period, the forest absorbed 1,092,037 Mg of C, but emitted 2908 Tg of C, which is 2.66-fold greater than the C absorbed, thereby compromising the role of the forest in acting as a C sink. Our findings show that environmental degradation caused by fires is related to the occurrence of dry periods in the Amazon Basin. [ABSTRACT FROM AUTHOR]

Cotton has high production costs compared to other annual crops because large numbers of plant protection product (PPP) applications can be needed to control insect pests, diseases, and growth. The hypothesis underlying this study was that vegetation indices (VIs) could be used to estimate application rates for cotton. Our objectives were to (i) evaluate the relationship between different VIs and the application rates for cotton; (ii) propose a modification to the canopy chlorophyll content index (CCCI); and (iii) to develop a VI based equation that will indicate the ideal application rate needed to maximize deposition in the middle layer of a cotton crop. The experiments were carried out during the crop seasons 2017/18, and 2018/19 in the State of Mato Grosso do Sul, Brazil. A multispectral sensor installed in an unmanned aerial vehicle (UAV) was used to obtain the VIs, and the application rates evaluated were 40, 70, 100, and 130 L ha−1. The spray deposits on cotton leaves were measured using the mass balance analysis method. Our findings revealed that an increase in the VIs led to a rise in the application rate needed to maintain spray deposition on the middle layer of cotton plants. The CCCI is related to the rate variation in the cotton crop. However, our results showed that the proposed modified equation (the simplified modified canopy chlorophyll content index), which is based on the relative deposition, improves the estimation of the application rate that will optimize spray deposition in the middle layer of cotton plants. [ABSTRACT FROM AUTHOR]

Wildfires in the Amazon biome of Mato Grosso cause extensive environmental, economic, and health damages, including biodiversity loss and high greenhouse gas emissions. This study used remote sensing to examine the relationship between fire severity and climatic factors, focusing on dNBR (Differenced Normalized Burn Ratio), precipitation, LST (Land Surface Temperature), SPI (Standardized Precipitation Index), NDVI (Normalized Difference Vegetation Index), and VCI (Vegetation Condition Index), analyzing data from 2001 to 2022. Statistical tests included Shapiro-Wilk, Tukey, regression kriging, Mann-Kendall for trend analysis, Pettitt for change points, and canonical variable tests. Regarding trends, only LST showed a significant trend starting in 2009, with the Northeast mesoregion showing the highest impact on temperature. dNBR correlated positively with NDVI and VCI, and negatively with precipitation and SPI. The northern mesoregion had a positive influence on dNBR and NDVI but negative for precipitation, SPI, and VCI. The southwestern mesoregion associated positively with dNBR and LST but negatively with the other variables. The Northeast and South-Central mesoregions showed positive correlations with most variables except dNBR and NDVI. These findings highlight the northern mesoregion's vulnerability due to its proximity to the central Amazon Forest and agri-cultural activity, indicating increased fire susceptibility with reduced humidity. • The northeast mesoregion of the Mato Grosso Amazon had the greatest impact on temperature. • There is vulnerability in the northern mesoregion due to its proximity to the central rainforest and agricultural activity. • The main positive correlations for dNBR were with the variables NDVI and VCI. [ABSTRACT FROM AUTHOR]

[Display omitted] • Hyperspectral reflectance for the levels of Asian soybean rust severity showed differences across the entire electromagnetic spectrum. • Plants with 50% disease severity have a curve close to healthy plants with lower reflectance. • More severely attacked plants have higher reflectance. Traditional monitoring of asian soybean rust severity is a time- and labor-intensive task, as it requires visual assessments by skilled professionals in the field. Thus, the use of remote sensing and machine learning (ML) techniques in data processing has emerged as an approach that can increase efficiency in disease monitoring, enabling faster, more accurate and time- and labor-saving evaluations. The aims of the study were: (i) to identify the spectral signature of different levels of Asian soybean rust severity; (ii) to identify the most accurate machine learning algorithm for classifying disease severity levels; (iii) which spectral input provides the highest classification accuracy for the algorithms; (iv) to determine a sample size of leaves that guarantees the best accuracy for the algorithms. A field experiment was carried out in the 2022/2023 harvest in a randomized block design with a 6x3 factorial scheme (ML algorithms x severity levels) and four replications. Disease severity levels assessed were: healthy leaves, 25 % severity, and 50 % severity. Leaf hyperspectral analysis was carried out over a wide range from 350 to 2500 nm. From this analysis, 28 spectral bands were extracted, seeking to distinguish the spectral signature for each severity level with the least input dataset. Data was subjected to machine learning analysis using Artificial Neural Network (ANN), REPTree (DT) and J48 decision trees, Random Forest (RF), and Support Vector Machine (SVM) algorithms, as well as a traditional classification method (Logistic Regression - LR). Two different input datasets were tested for each algorithm: the full spectrum (ALL) provided by the sensor and the 28 spectral bands (SB). Tests with different sample sizes were also conducted to investigate the algorithms' ability to detect severity levels with a reduced sample size. Our findings indicate differences between the spectral curves for the severity levels assessed, which makes it possible to differentiate between healthy plants with low and high severity using hyperspectral sensing. SVM was the most accurate algorithm for classifying severity levels by using all the spectral information as input. This algorithm also provided high classification accuracy when using smaller leaf samples. This study reveals that hyperspectral sensing and the use of ML algorithms provide an accurate classification of different levels of Asian rust severity, and can be powerful tools for a more efficient disease monitoring process. [ABSTRACT FROM AUTHOR]

• Real-time monitoring of boron fertilization in eucalyptus is helpful for guiding precision diagnosis; • The 350–371 nm spectral range can be used for detecting boron-deficient plants; • Adequate boron levels can be identified by using the 426–444, 1811–1910, 1948–2115, and 2124–2208 nm; • The 425–475 nm spectral range can be used to find boron-toxicity plants. Boron (B) is an essential element whose deficiency results in rapid inhibition in the growth of plants, acting on their meristematic growth. Real-time monitoring of B fertilization in eucalyptus is helpful for guiding precision diagnosis and efficient management of plant boron nutrition. This research hypothesizes that different boron levels alter the reflectance of different wavelengths in eucalyptus. In this context, the objective of this study was to identify spectral ranges that can be used to monitor the boron status in eucalyptus plants. The experiment was carried out in a greenhouse, in which the treatments consisted of increasing boron levels in the form of boric acid (17% of B), whose levels varied from deficit to toxicity. Thus, five treatments were established: no boron, 1, 10, 20, and 40 mg/dm3 of boron. The remote sensing data used were bands, heights, and vegetation indices calculated after obtaining the spectral curves in each treatment. Our findings show that it is possible to accurately distinguish the boron levels in eucalyptus using hyper and multispectral bands. The 350–371 nm spectral range can be used for detecting boron-deficient plants. Plants with adequate boron levels can be identified by using the 426–444 nm, 1811–1910 nm, 1948–2115 nm, and 2124–2208 nm spectral ranges. Finally, the 425–475 nm spectral range can be used to find boron-toxicity plants. [ABSTRACT FROM AUTHOR]

Greenhouse gas (GHG) sources and sinks are an important global concern. Monitoring the spatiotemporal variations of GHG concentrations, particularly carbon dioxide (CO 2), is crucial for identifying potential sources and sinks and moving toward a sustainable future. Therefore, via a time-series of remote data and multispectral images, this study evaluates the CO 2 spatiotemporal dynamics and related factors during 2015–2018 in one of the world's main agricultural frontier areas, the state of Mato Grosso (SMT), Brazil, which is both experiencing continued deforestation and attempting to achieve sustainable food production. In this study, data was obtained from the measurement of column-averaged carbon dioxide (CO 2) dry air mole fraction in the atmosphere, set as X CO2 from Orbiting Carbon Observatory-2 satellite from January 2015 to December 2018. The enhanced vegetation index data were obtained from the Moderate-Resolution Imaging Spectroradiometer (MODIS) sensor, and rainfall data were obtained from the Climate Hazards Group InfraRed Precipitation with Station dataset. From a series of Landsat-8 satellite images, it was possible to distinguish land use and land cover classes and estimate the CO 2 flux in the SMT. The results showed that the temporal variability of CO 2 flux is correlated positively with rainfall, while X CO2 is negatively correlated with rainfall. Regarding spatial variability, we observed that forest areas that were converted to other land uses resulted in higher values that characterize with sources, and that the highest and lowest average concentrations of CO 2 occurred in the dry and rainy months, respectively, for X CO2 , which might be the result of differences in the vertical resolution of the CO 2 column and scale. In contrast, areas with large continuous forest areas tended to have lower values and contribute positively to the carbon balance as sinks, thereby mitigating climate change impacts. Therefore, not only X CO2 but also CO 2 flux are directly related to changes in land use and land cover (LULC) in complex systems that are affected by climatic variables and processes, such as photosynthesis and soil respiration. • X CO2 is inversely related to rainfall, with highest concentration in drier periods. • Human actions in land use and land cover change increase atmospherical CO 2. • Remote sensing to locate and understand the sources and sinks of carbon dioxide. [ABSTRACT FROM AUTHOR]